Triple

T22088919
Position Surface form Disambiguated ID Type / Status
Subject Ian Duncan E545861 entity
Predicate portrayedBy P1507 FINISHED
Object John Oliver 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 Oliver | Statement: [Ian Duncan, portrayedBy, John Oliver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Oliver
Context triple: [Ian Duncan, portrayedBy, John Oliver]
  • A. John Oliver chosen
    John Oliver is a British-American comedian and political satirist best known as the host of the HBO news-comedy show "Last Week Tonight with John Oliver."
  • B. Jon Stewart
    Jon Stewart is an American comedian, writer, producer, and former host of "The Daily Show," widely known for his sharp political satire and influence on contemporary news comedy.
  • C. Kevin Maher
    Kevin Maher is an English former professional footballer and current football manager best known for his long association with Southend United.
  • D. Stephen Colbert
    Stephen Colbert is an American comedian, writer, producer, political satirist, and television host best known for his work on "The Colbert Report" and "The Late Show with Stephen Colbert."
  • E. Sean Maher
    Sean Maher is an American actor best known for playing Dr. Simon Tam in the television series "Firefly" and its film continuation "Serenity."
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e47ba08190a208af72a7cc176f completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.