Triple

T7581178
Position Surface form Disambiguated ID Type / Status
Subject The Winds of War E179488 entity
Predicate castMember P1668 FINISHED
Object David Dukes E593561 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: David Dukes | Statement: [The Winds of War, castMember, David Dukes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Dukes
Context triple: [The Winds of War, castMember, David Dukes]
  • A. David Dukes chosen
    David Dukes was an American character actor known for his extensive work in film, television, and theater from the 1970s through the 1990s.
  • B. Robert Dukes
    Robert Dukes is an author best known for writing the second installment of the "Bound" series.
  • C. Alan Dukes
    Alan Dukes is an Irish economist and former politician who served as leader of the Fine Gael party and held several senior ministerial roles.
  • D. Kevin Duckworth
    Kevin Duckworth was an American NBA center best known for his All-Star years with the Portland Trail Blazers in the late 1980s and early 1990s.
  • E. John Hemenway Duncan
    John Hemenway Duncan was an American architect best known for designing prominent late-19th-century monuments and public structures in New York City.
  • 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_69c69f327db881909a21ae3b156f8ded completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c6f97717048190b0ca1a74ed8a817e completed March 27, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c861735c7c81908e2c9fcbb1005ec3 completed March 28, 2026, 11:17 p.m.
Created at: March 27, 2026, 3:52 p.m.