Triple

T10493178
Position Surface form Disambiguated ID Type / Status
Subject A Woman's Devotion E247468 entity
Predicate screenwriter P2831 FINISHED
Object Robert Hill E500467 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: Robert Hill | Statement: [A Woman's Devotion, screenwriter, Robert Hill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Hill
Context triple: [A Woman's Devotion, screenwriter, Robert Hill]
  • A. Robert Hill chosen
    Robert Hill was a screenwriter known for his work on the film "The Big Operator" and other mid-20th-century American movies.
  • B. David Wolstencroft
    David Wolstencroft is a British television writer and producer best known for his work in the spy thriller genre.
  • C. Edward Troup
    Edward Troup is a British tax lawyer and civil servant best known for serving as Executive Chair of HM Revenue and Customs (HMRC).
  • D. George Barr
    George Barr is a science fiction and fantasy fan artist renowned for his distinctive illustrative work, which earned him recognition such as the Hugo Award for Best Fan Artist.
  • E. George Barr
    George Barr was a prominent Major League Baseball umpire active in the mid-20th century, known for officiating numerous significant games and for helping to professionalize umpire training.
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5097ecbec8190807c4fcc85662026 completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d8dcaeb6088190829b6c26eb1de7d5 completed April 10, 2026, 11:19 a.m.
Created at: April 6, 2026, 12:24 p.m.