{"_id": {"$oid": "69d4eb12b877594bc57189c1"}, "test_id": "T0307", "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": "openai", "model": "gpt-4.1-mini", "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": "openai", "model": "gpt-4.1-mini", "duration": 2.7811131477355957, "timestamp": "2025-10-24T14:36:41.037444", "parsed": {"company": {"transcription": "Gittard L\u00e9on"}, "location": {"transcription": "Gen\u00e8ve"}, "b_id": {"transcription": "B.51.322.GB.759"}, "date": "1942-12-02", "information": [{"transcription": "Figuriert auf Amendment 18, Nov.1942, zur britischen schwarzen Liste."}, {"transcription": "Gestrichen !\nAmendment 13, 24. Oktober 1944."}, {"transcription": "fig. noch auf franz. Liste Suppl. 6, 31.8.44"}]}, "text": "", "raw_response": {"id": "chatcmpl-CUBK2RWMeyqhsiWdB6yig8FSHPpsx", "model": "gpt-4.1-mini-2025-04-14", "choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "{\"company\":{\"transcription\":\"Gittard L\u00e9on\"},\"location\":{\"transcription\":\"Gen\u00e8ve\"},\"b_id\":{\"transcription\":\"B.51.322.GB.759\"},\"date\":\"1942-12-02\",\"information\":[{\"transcription\":\"Figuriert auf Amendment 18, Nov.1942, zur britischen schwarzen Liste.\"},{\"transcription\":\"Gestrichen !\\nAmendment 13, 24. Oktober 1944.\"},{\"transcription\":\"fig. noch auf franz. Liste Suppl. 6, 31.8.44\"}]}", "role": "assistant"}}], "usage": {"prompt_tokens": 1723, "completion_tokens": 122, "total_tokens": 1845}}, "usage": {"input_tokens": 1723, "output_tokens": 122, "total_tokens": 1845}, "finish_reason": "stop"}, "scoring": {"fuzzy": 0.9565127602893654, "cost_summary": {"total_input_tokens": 56235, "total_output_tokens": 3085, "total_tokens": 59320, "input_cost_usd": 0.022494, "output_cost_usd": 0.004936, "total_cost_usd": 0.02743, "pricing_date": "2025-10-24", "input_price_per_million": 0.4, "output_price_per_million": 1.6}}, "normalized_score": 95.65127602893654}