Triple

T23321965
Position Surface form Disambiguated ID Type / Status
Subject Jacques Marin E591174 entity
Predicate workedWith P398 FINISHED
Object Arthur Hiller NE NERFINISHED

How this triple was built (2 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: Arthur Hiller | Statement: [Jacques Marin, workedWith, Arthur Hiller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Arthur Hiller
Context triple: [Jacques Marin, workedWith, Arthur Hiller]
  • A. Arthur Hiller chosen
    Arthur Hiller was a Canadian-born film director best known for popular Hollywood movies such as "Love Story" and "The In-Laws."
  • B. Herbert Ross
    Herbert Ross was an American choreographer and film director known for his work on Broadway and in Hollywood, including acclaimed movies such as "The Goodbye Girl" and "Steel Magnolias."
  • C. Franklin J. Schaffner
    Franklin J. Schaffner was an American film and television director best known for acclaimed works such as "Patton," "Planet of the Apes," and "Papillon."
  • D. Ott Heller
    Ott Heller was a Canadian professional ice hockey defenseman best known for his years with the New York Rangers in the NHL, where he won the Stanley Cup in 1940.
  • E. Richard Fleischer
    Richard Fleischer was an American film director known for a diverse body of work that included noir, science fiction, historical epics, and big-budget Hollywood adventures.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e25d1effe4819096907f95f610dbff completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f1978672148190bb90804361bb896b completed April 29, 2026, 5:30 a.m.
Created at: April 17, 2026, 5:07 p.m.