Triple

T16537967
Position Surface form Disambiguated ID Type / Status
Subject Robert Sisk E401741 entity
Predicate collaboratedWith P435 FINISHED
Object John Farrow E454406 NE FINISHED

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: John Farrow | Statement: [Robert Sisk, collaboratedWith, John Farrow]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Farrow
Context triple: [Robert Sisk, collaboratedWith, John Farrow]
  • A. John Farrow chosen
    John Farrow was an Academy Award–winning Australian-born film director, screenwriter, and producer active in Hollywood during the mid-20th century.
  • B. Peter Neal
    Peter Neal is an American lawyer known for being married to Naomi Biden, the granddaughter of U.S. President Joe Biden.
  • C. Farley Granger
    Farley Granger was an American actor best known for his roles in classic mid-20th-century films such as Alfred Hitchcock’s "Rope" and "Strangers on a Train."
  • D. Joel Harlow
    Joel Harlow is an Academy Award-winning American makeup artist and special effects designer known for his work on films such as "Star Trek" and "Pirates of the Caribbean."
  • E. Michael Curtis
    Michael Curtis is a film and television producer known for serving as an executive producer on projects such as those involving Jonas L.A.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d88384bc30819084229e7dcdc39a41 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e34559ca948190a9eb810b9b3be079 completed April 18, 2026, 8:48 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00aae69d1481909f5514cc496f45b5 completed May 10, 2026, 3:57 p.m.
Created at: April 10, 2026, 5:15 a.m.