{"_id": {"$oid": "69d4eb12b877594bc57189ce"}, "test_id": "T0318", "benchmark": "blacklist_cards", "date": "2025-10-24", "tags": {"document-type": ["index-card"], "writing": ["typed", "handwritten"], "century": [20], "language": ["de"], "entry-type": ["company"], "task": ["information-extraction"]}, "contributors": ["lea_kasper", "sorin_marti"], "hidden": false, "config": {"provider": "genai", "model": "gemini-2.5-flash-lite-preview-09-2025", "dataclass": "Card", "temperature": 0.5, "role_description": "You are a Historian", "prompt_file": "prompt.txt", "legacy_test": false}, "prompt": "You are a meticulous archivist extracting data from an index card image. Analyze the provided image and extract the following information. Return the data ONLY as a valid JSON object.\n\n- \"company\": The primary company name, usually in the top-left. Exclude the location.\n- \"location\": The city or town, often following the company name.\n- \"b_id\": The identifier code, usually in the top-right, starting with \"B.\".\n- \"date\": Any stamped dates on the card in YYYY-MM-DD format. If no date is present, use an empty string.\n- \"information\": A list of text blocks from the main body of the card. Each block should be a separate string in the list. Maintain line breaks with \\\\n.\n\nHere is the required JSON format:\n{\n  \"company\": {\"transcription\": \"\"},\n  \"location\": {\"transcription\": \"\"},\n  \"b_id\": {\"transcription\": \"\"},\n  \"date\": \"\",\n  \"information\": [\n    {\"transcription\": \"\"}\n  ]\n}\n\nIf you cannot find a value for a field, leave its transcription value as an empty string. Do not add any explanatory text outside of the JSON object.", "results": {"provider": "genai", "model": "gemini-2.5-flash-lite-preview-09-2025", "duration": 0.878354549407959, "timestamp": "2025-10-24T16:30:44.340740", "parsed": {"company": {"transcription": "Spuhler Clemens"}, "location": {"transcription": "Z\u00fcrich"}, "b_id": {"transcription": "B.51.322.GB.1263"}, "date": "1945-11-23", "information": [{"transcription": "Britische schwarze Liste,\nAmendment 2, Februar 1944."}, {"transcription": "gestrichen:\nAmendment 13, 23.11.1945."}]}, "text": "{\n  \"company\": {\n    \"transcription\": \"Spuhler Clemens\"\n  },\n  \"location\": {\n    \"transcription\": \"Z\u00fcrich\"\n  },\n  \"b_id\": {\n    \"transcription\": \"B.51.322.GB.1263\"\n  },\n  \"date\": \"1945-11-23\",\n  \"information\": [\n    {\n      \"transcription\": \"Britische schwarze Liste,\\nAmendment 2, Februar 1944.\"\n    },\n    {\n      \"transcription\": \"gestrichen:\\nAmendment 13, 23.11.1945.\"\n    }\n  ]\n}", "raw_response": {"text": "{\n  \"company\": {\n    \"transcription\": \"Spuhler Clemens\"\n  },\n  \"location\": {\n    \"transcription\": \"Z\u00fcrich\"\n  },\n  \"b_id\": {\n    \"transcription\": \"B.51.322.GB.1263\"\n  },\n  \"date\": \"1945-11-23\",\n  \"information\": [\n    {\n      \"transcription\": \"Britische schwarze Liste,\\nAmendment 2, Februar 1944.\"\n    },\n    {\n      \"transcription\": \"gestrichen:\\nAmendment 13, 23.11.1945.\"\n    }\n  ]\n}", "usage_metadata": {"prompt_token_count": 523, "candidates_token_count": 169, "total_token_count": 692}}, "usage": {"input_tokens": 523, "output_tokens": 169, "total_tokens": 692}, "finish_reason": "stop"}, "scoring": {"fuzzy": 0.8539860824339851, "cost_summary": {"total_input_tokens": 17259, "total_output_tokens": 5684, "total_tokens": 22943, "input_cost_usd": 0.001726, "output_cost_usd": 0.002274, "total_cost_usd": 0.004, "pricing_date": "2025-10-24", "input_price_per_million": 0.1, "output_price_per_million": 0.4}}, "normalized_score": 85.39860824339851}