Triple

T12385751
Position Surface form Disambiguated ID Type / Status
Subject Geoffrey Unsworth E295858 entity
Predicate workedOn P3 FINISHED
Object Becket E242033 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: Becket | Statement: [Geoffrey Unsworth, workedOn, Becket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Becket
Context triple: [Geoffrey Unsworth, workedOn, Becket]
  • A. Becket
    Becket is a small rural town in western Massachusetts known for its scenic Berkshire landscapes and outdoor recreation.
  • B. Becket
    Becket is a surname most notably associated with figures such as the American modernist architect Welton Becket.
  • C. Becket chosen
    Becket is a 1964 historical drama film about the conflict between King Henry II and Archbishop Thomas Becket, renowned for its powerful performances and exploration of church–state tensions.
  • D. Becket’s Crown
    Becket’s Crown is an alternative name for the Corona Chapel, a notable architectural feature of Canterbury Cathedral traditionally associated with the relics of Saint Thomas Becket.
  • E. Good King Henry
    Good King Henry is the popular epithet of Henry IV of France, the first Bourbon king renowned for ending the French Wars of Religion and issuing the Edict of Nantes to promote religious tolerance.
  • 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_69d6ad9e653c8190b1473c860ee53dae completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d93fbd489c819098233a111442762e completed April 10, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6347816408190904ea71d2a72398f completed May 2, 2026, 5:29 p.m.
Created at: April 8, 2026, 9:54 p.m.