Triple

T21159947
Position Surface form Disambiguated ID Type / Status
Subject Two Arabian Knights E521412 entity
Predicate stars P1956 FINISHED
Object William Boyd 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: William Boyd | Statement: [Two Arabian Knights, stars, William Boyd]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: William Boyd
Context triple: [Two Arabian Knights, stars, William Boyd]
  • A. William Boyd chosen
    William Boyd was an American actor best known for portraying the cowboy hero Hopalong Cassidy in numerous films and early television.
  • B. William Boyd
    William Boyd is a Scottish novelist and screenwriter acclaimed for his richly crafted literary fiction, including works such as "Any Human Heart" and "A Good Man in Africa."
  • C. David de Kretser
    David de Kretser is an Australian medical researcher and academic who served as the 27th Governor of Victoria.
  • D. Louis de Bernières
    Louis de Bernières is a British novelist best known for works such as "Captain Corelli’s Mandolin" and the novella "Red Dog," which inspired the film of the same name.
  • E. Gregg Mayles
    Gregg Mayles is a British video game designer best known for his long-time work at Rare on classic titles such as the Donkey Kong Country series and Banjo-Kazooie.
  • 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_69e0b50d1ea481909c07e63c3ead9316 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7252f70888190b8e6109cc4099ecc completed April 21, 2026, 7:20 a.m.
Created at: April 16, 2026, 2:59 p.m.