Triple

T6812869
Position Surface form Disambiguated ID Type / Status
Subject In Name Only E156678 entity
Predicate director P255 FINISHED
Object John Cromwell E333704 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 Cromwell | Statement: [In Name Only, director, John Cromwell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Cromwell
Context triple: [In Name Only, director, John Cromwell]
  • A. John Cromwell chosen
    John Cromwell was an American film and stage director and actor best known for his work in classic Hollywood cinema during the 1930s and 1940s.
  • B. Robert Cromwell
    Robert Cromwell was an English country gentleman of the late 16th and early 17th centuries, best known as the father of Oliver Cromwell, the future Lord Protector of England.
  • C. John Throckmorton
    John Throckmorton was a 17th-century English settler and landowner in the American colonies, after whom the New York neighborhood of Throggs Neck is named.
  • D. Edmund Bonner
    Edmund Bonner was a 16th-century English bishop of London notorious for his zealous role in persecuting Protestants during the reign of Mary I.
  • E. William Waynflete
    William Waynflete was a 15th-century English bishop, Lord Chancellor, and prominent educational patron best known for his role in the development of Oxford University.
  • 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_69c68828b26c819090fe9df7612bbc27 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d329861881909f65bd1017ea384b completed March 27, 2026, 6:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72f9d19bc8190bbdc20178239bae1 completed March 28, 2026, 1:32 a.m.
Created at: March 27, 2026, 2:17 p.m.