Triple

T23264312
Position Surface form Disambiguated ID Type / Status
Subject Dirty Mary, Crazy Larry E582103 entity
Predicate director P255 FINISHED
Object John Hough 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: John Hough | Statement: [Dirty Mary, Crazy Larry, director, John Hough]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Hough
Context triple: [Dirty Mary, Crazy Larry, director, John Hough]
  • A. John Hough chosen
    John Hough is a British film and television director best known for his work in horror and genre cinema during the 1970s and 1980s.
  • B. Bob Houghton
    Bob Houghton is an English football manager best known for his influential tactical innovations in the 1970s, including leading Malmö FF to the 1979 European Cup final.
  • C. Joe Crozier
    Joe Crozier was a Canadian ice hockey defenceman and coach best known for his long minor-league career and later coaching roles in the NHL and WHA.
  • D. Phil Ball
    Phil Ball was an early 20th-century American businessman and baseball executive best known for his ownership role in professional teams, including in the Federal League.
  • E. John Bowman
    John Bowman was a 19th-century American politician who served in a key statewide infrastructure and regulatory role in New York.
  • 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_69e246079f58819085eaa9c260906880 completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f194cb76c48190869915cd93b44fcc completed April 29, 2026, 5:19 a.m.
Created at: April 17, 2026, 4:11 p.m.