{"_id": {"$oid": "69d4eb12b877594bc5718a4b"}, "test_id": "T0405", "benchmark": "business_letters", "date": "2025-11-25", "tags": {"document-type": ["letter"], "writing": ["typed", "handwritten"], "century": [20], "language": ["de"], "layout": ["prose"], "entry-type": ["person", "location"], "task": ["information-extraction"]}, "contributors": ["eric_decker", "maximilian_hindermann", "lea_kasper", "anthea_alberto", "pema_frick", "jose_luis_losada_palenzuela", "sorin_marti", "elena_spadini"], "hidden": false, "config": {"provider": "openai", "model": "gpt-5.1-2025-11-13", "dataclass": "Document", "temperature": 0.0, "role_description": "You are a historian with keyword knowledge and an expert in the field of 20th century Swiss history", "prompt_file": "prompt.txt", "rules": "{\"skip_signatures\": true, \"skip_non_signatures\": false}", "legacy_test": false}, "prompt": "            IDENTITY and PURPOSE:\n\n            You are presented with a series of images constituting a historical letter. Your task is to extract the\n            values of the following keys from the letter and return them in a JSON file where the values\n            corresponding to each key should be stored as a list, even if there is only a single value for a\n            key:\n\n            - letter_title: Title of the letter.\n            - sender_persons: Name(s) of the person(s) who wrote the letter.\n            - send_date: The exact or approximate date the letter was written.\n            - receiver_persons: Name(s) of the person(s) who received the letter.\n\n            Take a deep breath and think step by step about how to best accomplish this goal. Map out all the claims\n            and implications on a virtual whiteboard in your mind. Do not use OCR. Use the ISO format YYYY-MM-DD for\n            dates. If a piece of information is not included in the letter, set the value for the corresponding key\n            to \"null\". Do not return anything except the JSON file.\n\n            EXAMPLE:\n\n            {\n                \"letter_title\": [\"Petition for Environmental Protection\"],\n                \"send_date\": [\"1993-03-12\"],\n                \"sender_persons\": [\"Lisa Simpson\"],\n                \"receiver_persons\": [\"Mayor Joe Quimby\", \"Seymour Skinner\"],\n            }\n\n            OUTPUT:", "results": {"text": "{\"metadata\":{\"send_date\":[\"1928-04-25\"],\"letter_title\":[\"\"],\"sender_persons\":[\"\"],\"receiver_persons\":[\"Basler Rheinschiffahrt A.G.\"]}}", "model": "gpt-5.1-2025-11-13", "provider": "openai", "finish_reason": "stop", "usage": {"input_tokens": 1398, "output_tokens": 53, "total_tokens": 1451}, "duration": 4.159851551055908, "timestamp": "2025-11-25T10:01:58.252434", "parsed": {"metadata": {"send_date": ["1928-04-25"], "letter_title": [""], "sender_persons": [""], "receiver_persons": ["Basler Rheinschiffahrt A.G."], "document_number": "letter28"}}, "score": {"send_date_tp": 1, "send_date_fp": 0, "send_date_fn": 0, "sender_persons_tp": 0, "sender_persons_fp": 0, "sender_persons_fn": 0, "receiver_persons_tp": 0, "receiver_persons_fp": 1, "receiver_persons_fn": 0}, "raw_response": "{\"id\":\"chatcmpl-CfjDouwoWBATWyJoF9e57wzMwjeOY\",\"choices\":[{\"finish_reason\":\"stop\",\"index\":0,\"logprobs\":null,\"message\":{\"content\":\"{\\\"metadata\\\":{\\\"send_date\\\":[\\\"1928-04-25\\\"],\\\"letter_title\\\":[\\\"\\\"],\\\"sender_persons\\\":[\\\"\\\"],\\\"receiver_persons\\\":[\\\"Basler Rheinschiffahrt A.G.\\\"]}}\",\"refusal\":null,\"role\":\"assistant\",\"annotations\":[],\"audio\":null,\"function_call\":null,\"tool_calls\":null,\"parsed\":{\"metadata\":{\"send_date\":[\"1928-04-25\"],\"letter_title\":[\"\"],\"sender_persons\":[\"\"],\"receiver_persons\":[\"Basler Rheinschiffahrt A.G.\"]}}}}],\"created\":1764061316,\"model\":\"gpt-5.1-2025-11-13\",\"object\":\"chat.completion\",\"service_tier\":\"default\",\"system_fingerprint\":null,\"usage\":{\"completion_tokens\":53,\"prompt_tokens\":1398,\"total_tokens\":1451,\"completion_tokens_details\":{\"accepted_prediction_tokens\":0,\"audio_tokens\":0,\"reasoning_tokens\":0,\"rejected_prediction_tokens\":0},\"prompt_tokens_details\":{\"audio_tokens\":0,\"cached_tokens\":1280}}}"}, "scoring": {"f1_macro": 0.48, "f1_micro": 0.57, "cost_summary": {"total_input_tokens": 44050, "total_output_tokens": 1475, "total_tokens": 45525, "input_cost_usd": 0.05506249999999998, "output_cost_usd": 0.014750000000000001, "total_cost_usd": 0.06981249999999999}}, "normalized_score": 48.0}