{"_id": {"$oid": "69d4eb12b877594bc57189cb"}, "test_id": "T0306", "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-4o-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-4o-mini", "duration": 4.250624418258667, "timestamp": "2025-10-24T14:35:30.509434", "parsed": {"company": {"transcription": "Skiff A.G."}, "location": {"transcription": "Luzern"}, "b_id": {"transcription": "B.51.322.GB.976."}, "date": "1943-04-05", "information": [{"transcription": "Britische schwarze Liste,\n amendment 5, April 1943."}, {"transcription": "gestrichen:\n Amendment 3, M\u00e4rz 1944."}]}, "text": "", "raw_response": {"id": "chatcmpl-CUBIteNq263sLnXZxDPeEOOZQYkac", "model": "gpt-4o-mini-2024-07-18", "choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "{\n  \"company\": {\"transcription\": \"Skiff A.G.\"},\n  \"location\": {\"transcription\": \"Luzern\"},\n  \"b_id\": {\"transcription\": \"B.51.322.GB.976.\"},\n  \"date\": \"1943-04-05\",\n  \"information\": [\n    {\"transcription\": \"Britische schwarze Liste,\\n amendment 5, April 1943.\"},\n    {\"transcription\": \"gestrichen:\\n Amendment 3, M\u00e4rz 1944.\"}\n  ]\n}", "role": "assistant"}}], "usage": {"prompt_tokens": 25978, "completion_tokens": 113, "total_tokens": 26091}}, "usage": {"input_tokens": 25978, "output_tokens": 113, "total_tokens": 26091}, "finish_reason": "stop"}, "scoring": {"fuzzy": 0.7792073402712372, "cost_summary": {"total_input_tokens": 857274, "total_output_tokens": 4493, "total_tokens": 861767, "input_cost_usd": 0.128591, "output_cost_usd": 0.002696, "total_cost_usd": 0.131287, "pricing_date": "2025-10-24", "input_price_per_million": 0.15, "output_price_per_million": 0.6}}, "normalized_score": 77.92073402712371}