Triple

T22254696
Position Surface form Disambiguated ID Type / Status
Subject Zulu E550067 entity
Predicate screenwriter P2831 FINISHED
Object John Prebble 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: John Prebble | Statement: [Zulu, screenwriter, John Prebble]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Prebble
Context triple: [Zulu, screenwriter, John Prebble]
  • A. John Prebble chosen
    John Prebble was a British-Canadian writer and historian best known for his popular works on Scottish history and for writing the screenplay for the film "Zulu."
  • B. John Ackroyd
    John Ackroyd was a British engineer best known for designing the Thrust2 jet-powered car that set the world land speed record in 1983.
  • C. Philip Moxham
    Philip Moxham is a Welsh bassist best known for his work with the influential post-punk band Young Marble Giants.
  • D. Bernard Bresslaw
    Bernard Bresslaw was a British comic actor best known for his towering height and recurring roles in the "Carry On" film series.
  • E. Cyril Mardall
    Cyril Mardall was an architect known for his work on major cultural venues, including the design of the Joseph Meyerhoff Symphony Hall in Baltimore.
  • 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_69e11e42adb8819087714772ea606709 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f138c1d70881908df47b0f818c0022 completed April 28, 2026, 10:46 p.m.
Created at: April 16, 2026, 8:39 p.m.