Triple

T20154815
Position Surface form Disambiguated ID Type / Status
Subject Mad Max E491529 entity
Predicate editor P1954 FINISHED
Object Tony Paterson 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: Tony Paterson | Statement: [Mad Max, editor, Tony Paterson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tony Paterson
Context triple: [Mad Max, editor, Tony Paterson]
  • A. Tony Paterson chosen
    Tony Paterson is a film editor best known for his work on the influential Australian action film "Mad Max."
  • B. Alastair Kennett
    Alastair Kennett is one of the children of former Victorian Premier and prominent Australian businessman Jeff Kennett.
  • C. David Agnew
    David Agnew is a pseudonymous writer credit used by the BBC, notably on the Doctor Who serial "City of Death," to represent work by multiple or uncredited contributors.
  • D. Roy Urquhart
    Roy Urquhart was a British Army major-general best known for leading the 1st Airborne Division during World War II, particularly in the failed Operation Market Garden at Arnhem in 1944.
  • E. Sir John Lyons
    Sir John Lyons was a prominent British linguist renowned for his influential work in semantics and the philosophy of language.
  • 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_69da6265f8f0819080b29c752a574088 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e667df7ac081908816d2d29e7c6513 completed April 20, 2026, 5:52 p.m.
Created at: April 11, 2026, 11:34 p.m.