Triple

T2459463
Position Surface form Disambiguated ID Type / Status
Subject Rollerball E54496 entity
Predicate editor P1954 FINISHED
Object Anthony Gibbs E252793 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: Anthony Gibbs | Statement: [Rollerball, editor, Anthony Gibbs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anthony Gibbs
Context triple: [Rollerball, editor, Anthony Gibbs]
  • A. Antony Gibbs chosen
    Antony Gibbs was a British film editor known for his work on influential films of the 1960s and 1970s.
  • B. Eric Gairy
    Eric Gairy was a Grenadian politician and trade union leader who served as the country’s first prime minister and was later overthrown in a 1979 coup.
  • C. Phil Harris
    Phil Harris was an American bandleader, singer, comedian, and radio personality best known for his wisecracking persona on classic radio shows and his later voice work in Disney animated films.
  • D. Michael Gibb
    Michael Gibb is one of the sons of Barry Gibb, the famed singer-songwriter and member of the Bee Gees.
  • E. Errol Christie
    Errol Christie was a British professional boxer and former amateur champion known for captaining the English amateur boxing team and competing as a middleweight in the 1980s.
  • 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_69ab49dee84c819096b50a0049c347ac completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abd10a35f88190b102a2cb5c88146e completed March 7, 2026, 7:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69af2b77207481909037a6ab4b420168 completed March 9, 2026, 8:20 p.m.
Created at: March 6, 2026, 9:44 p.m.