Triple

T3564516
Position Surface form Disambiguated ID Type / Status
Subject Training Day E75412 entity
Predicate producer P490 FINISHED
Object Andrew Z. Davis
Andrew Z. Davis is a film producer best known for his work on the crime thriller "Training Day."
 E381075 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Andrew Z. Davis | Statement: [Training Day, producer, Andrew Z. Davis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Andrew Z. Davis
Context triple: [Training Day, producer, Andrew Z. Davis]
  • A. Michael V. Drake
    Michael V. Drake is an American academic leader and physician who has served as president of both The Ohio State University and the University of California system.
  • B. Ben D. Waisbren
    Ben D. Waisbren is a film producer known for financing and producing major studio and independent movies.
  • C. Edward Reeves
    Edward Reeves was a teacher and mentor known for instructing Lionel Logue, the Australian speech therapist famous for treating King George VI.
  • D. Stephen M. Kellen
    Stephen M. Kellen was a prominent financier and philanthropist known for his leadership at Arnhold and S. Bleichroeder and his significant support of cultural and educational institutions.
  • E. Michael T. Williamson
    Michael T. Williamson is an American actor best known for his role as Benjamin Buford "Bubba" Blue in the film Forrest Gump.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Andrew Z. Davis
Triple: [Training Day, producer, Andrew Z. Davis]
Generated description
Andrew Z. Davis is a film producer best known for his work on the crime thriller "Training Day."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Andrew Z. Davis
Target entity description: Andrew Z. Davis is a film producer best known for his work on the crime thriller "Training Day."
  • A. Michael V. Drake
    Michael V. Drake is an American academic leader and physician who has served as president of both The Ohio State University and the University of California system.
  • B. Ben D. Waisbren
    Ben D. Waisbren is a film producer known for financing and producing major studio and independent movies.
  • C. Edward Reeves
    Edward Reeves was a teacher and mentor known for instructing Lionel Logue, the Australian speech therapist famous for treating King George VI.
  • D. Stephen M. Kellen
    Stephen M. Kellen was a prominent financier and philanthropist known for his leadership at Arnhold and S. Bleichroeder and his significant support of cultural and educational institutions.
  • E. Michael T. Williamson
    Michael T. Williamson is an American actor best known for his role as Benjamin Buford "Bubba" Blue in the film Forrest Gump.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69ad85d512708190829c8b2d3a2ccfb8 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc0a76c008190a2056b6d990776fe completed March 8, 2026, 6:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4cdd663a881908707ec3bc6a3ebcc completed March 14, 2026, 2:54 a.m.
NEDg Description generation batch_69b4ce445974819081b827cd3e9d15fc completed March 14, 2026, 2:56 a.m.
NED2 Entity disambiguation (via description) batch_69b4ce72e8d48190804d579cec4b4201 completed March 14, 2026, 2:56 a.m.
Created at: March 8, 2026, 3:21 p.m.