Triple

T21605106
Position Surface form Disambiguated ID Type / Status
Subject Bill Onus E533150 entity
Predicate knownAs P39 FINISHED
Object Bill Onus 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: Bill Onus | Statement: [Bill Onus, knownAs, Bill Onus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bill Onus
Context triple: [Bill Onus, knownAs, Bill Onus]
  • A. Bill Onus chosen
    Bill Onus was an influential Australian Aboriginal activist, cultural leader, and entrepreneur who played a key role in advancing Indigenous rights and visibility in the mid-20th century.
  • B. Buddy Sorrell
    Buddy Sorrell is a wisecracking comedy writer and supporting character on the classic American sitcom "The Dick Van Dyke Show."
  • C. Bernie Dodd
    Bernie Dodd is a driven Broadway director in the film "The Country Girl," whose demanding methods and personal struggles shape the story’s central drama.
  • D. Bill Marshall
    Bill Marshall was a Canadian film producer and cultural entrepreneur best known for co-founding and helping establish the Toronto International Film Festival as a major global cinema event.
  • E. Ron Osborn
    Ron Osborn is an American screenwriter and television writer-producer known for his work on films like "Meet Joe Black" and series such as "Moonlighting" and "The West Wing."
  • 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_69e0c46364608190a337dc8720dc2a35 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ef17e4a8088190bf51ab2af2369762 completed April 27, 2026, 8:01 a.m.
Created at: April 16, 2026, 6:33 p.m.