Triple

T17479263
Position Surface form Disambiguated ID Type / Status
Subject Boy A E425614 entity
Predicate director P255 FINISHED
Object John Crowley 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 Crowley | Statement: [Boy A, director, John Crowley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Crowley
Context triple: [Boy A, director, John Crowley]
  • A. John Crowley chosen
    John Crowley is an Irish film and theatre director best known for acclaimed dramas such as "Brooklyn" and "Boy A."
  • B. Cormac Wibberley
    Cormac Wibberley is an American screenwriter best known for co-writing the action-adventure film "National Treasure" and its sequel with his wife, Marianne Wibberley.
  • C. David Anthony Roberts
    David Anthony Roberts is the birth name of American actor Tony Roberts, known for his roles in numerous Woody Allen films and on Broadway.
  • D. Brian Hartnett
    Brian Hartnett is a notable individual distinguished enough in his field or public life to be specifically recognized as a bearer of the Hartnett surname.
  • E. Jeffrey Ford
    Jeffrey Ford is a film editor known for his work on major blockbuster movies, including several entries in the Marvel Cinematic Universe.
  • 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_69d889dbc2e88190b18ea6115e819258 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e451be5fd08190aeaa12b3a6d6c6d4 completed April 19, 2026, 3:53 a.m.
Created at: April 10, 2026, 5:48 a.m.