Triple

T20453035
Position Surface form Disambiguated ID Type / Status
Subject Do Revenge E501702 entity
Predicate cinematographyBy P1953 FINISHED
Object Brian Burgoyne 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: Brian Burgoyne | Statement: [Do Revenge, cinematographyBy, Brian Burgoyne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Burgoyne
Context triple: [Do Revenge, cinematographyBy, Brian Burgoyne]
  • A. Brian Burgoyne chosen
    Brian Burgoyne is a cinematographer known for his work on acclaimed independent films, including the romantic comedy-drama "The Big Sick."
  • B. Thomas Truxton
    Thomas Truxton was an American naval officer and early U.S. Navy captain renowned for his service during the Quasi-War with France.
  • C. Nicholas Bayard
    Nicholas Bayard was a prominent 17th-century New York colonial official and landowner, known for his influential role in early New Amsterdam politics and society.
  • D. Charles Wolfe
    Charles Wolfe was an Irish poet and clergyman best known for his elegiac poem "The Burial of Sir John Moore after Corunna."
  • E. John Burgoyne
    John Burgoyne was a British army officer and politician best known for his role as a general during the American Revolutionary War, particularly his surrender at the Battle of Saratoga in 1777.
  • 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_69e0b4ac0a1c81908845d0f8a56abce8 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e68d039af08190827bf765b50515a8 completed April 20, 2026, 8:30 p.m.
Created at: April 16, 2026, 11:32 a.m.