Search Test Runs

Test T0651 at 2026-03-16

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0663 at 2026-03-16

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0680 at 2026-03-16

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0639 at 2026-03-16

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0692 at 2026-03-16

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0601 at 2026-02-10

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0582 at 2026-02-10

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0608 at 2026-02-10

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0614 at 2026-02-10

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result

Test T0615 at 2026-02-10

{'document-type': ['index-card'], 'writing': ['handwritten', 'typed', 'printed'], 'century': [20], 'layout': ['table', 'form'], 'task': ['transcription', 'document-understanding', 'data-correction'], 'language': ['de', 'fr']}

Extract all information from this personnel card table and return it as a structured JSON object. The card contains rows documenting employment history with positions, locations, salary information, dates, and remarks.

REQUIRED JSON STRUCTURE:
```json
{
  "rows": [
    {
      "row_number": 1,
      "dienstliche_stellung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "dienstort": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "gehaltsklasse": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      },
      "jahresgehalt_monatsgehalt_taglohn": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "standardized numeric form or null",
        "is_crossed_out": false
      },
      "datum_gehaltsänderung": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "YYYY-MM-DD format or null",
        "is_crossed_out": false
      },
      "bemerkungen": {
        "diplomatic_transcript": "exact text from card",
        "interpretation": "expanded/standardized form or null",
        "is_crossed_out": false
      }
    }
  ]
}
```

COLUMN DEFINITIONS:
1. **dienstliche_stellung**: Official position or job title (e.g., "Assistent", "Professor", "Sekretär")
2. **dienstort**: Place of service or work location (e.g., "Basel", "Zürich")
3. **gehaltsklasse**: Salary class or grade (e.g., "III", "IV", roman numerals or numbers)
4. **jahresgehalt_monatsgehalt_taglohn**: Salary amount (annual/monthly/daily wage)
5. **datum_gehaltsänderung**: Date of salary change or effective date
6. **bemerkungen**: Remarks, notes, or additional comments

FIELD EXTRACTION RULES:

**diplomatic_transcript** (REQUIRED for all fields):
- Transcribe EXACTLY as written on the card
- Include all abbreviations, punctuation, and formatting as they appear
- Preserve original capitalization and spacing
- Include currency symbols and separators (e.g., "Fr. 2'400.-", "3.700.-")
- For dates, copy the exact format (e.g., "1. Jan. 1946", "1.April 1945")
- Use empty string "" for empty cells
- Be sure to escape ditto marks (repetition marks such as `"` indicating "same as above")
- DO NOT expand abbreviations or standardize formats
- Do not transcribe checkmarks

**interpretation** (OPTIONAL - use null if not applicable):
- For ditto marks (repetition marks such as `"`): Replace with the actual repeated value from the previous row in the same column
  - For example, if previous row's dienstliche_stellung is "Hilfsleiterin" and current row has `"`, interpret as "Hilfsleiterin"
  - Do NOT add explanatory text like "wie oben" or similar - just provide the repeated value
- Never expand abbreviations
- For dates: Convert to ISO format YYYY-MM-DD
  - "1. Jan. 1946" → "1946-01-01"
  - "1.April 1945" → "1945-04-01"
- For salary amounts: Extract numeric value only (remove currency symbols, separators)
  - "Fr. 2'400.-" → "2400"
  - "3.700.-" → "3700"
  - "5.094.-" → "5094"
  "6,30.-" → "6.3"
- For salary class: Convert roman numerals to arabic if clear
  - "III" → "3"
  - "IV" → "4"
- Do not convert roman numerals to arabic if not salary, date, or salary class
- Use null if no interpretation/expansion is needed or if the field is empty
- "+ {word}" where {word} is a word does not need interpretation

**is_crossed_out** (REQUIRED for all fields):
- Set to true if text in this field is crossed out, struck through, or deleted
- Set to false if text is normal (not crossed out)
- Empty cells should have is_crossed_out: false

ROW HANDLING:
- Number rows sequentially starting from 1 (top to bottom)
- Include ALL rows that have ANY content in ANY column
- Empty rows (all cells empty) should be omitted
- A row with only one filled cell should still be included

IMPORTANT NOTES:
- Return ONLY the JSON object, no additional text or explanation
- Every field must have all three sub-fields: diplomatic_transcript, interpretation, is_crossed_out
- diplomatic_transcript must never be null (use empty string "" for empty cells)
- interpretation can be null when no expansion/standardization applies
- Process the entire table from top to bottom
- Maintain consistent row numbering throughout

no valid result