Triple

T19543055
Position Surface form Disambiguated ID Type / Status
Subject Bradley Walsh E488956 entity
Predicate characterPortrayed P1507 FINISHED
Object Graham O'Brien 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: Graham O'Brien | Statement: [Bradley Walsh, characterPortrayed, Graham O'Brien]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Graham O'Brien
Context triple: [Bradley Walsh, characterPortrayed, Graham O'Brien]
  • A. Graham O'Brien chosen
    Graham O'Brien is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
  • B. Ken O'Brien
    Ken O'Brien is a former American football quarterback best known for his Pro Bowl career with the New York Jets in the 1980s.
  • C. Alex O’Brien
    Alex O’Brien is a former American professional tennis player best known for reaching the world No. 1 ranking in doubles and winning the 1999 US Open men’s doubles title.
  • D. Nick O'Brien
    Nick O'Brien is a hard-edged, morally ambiguous Los Angeles County Sheriff's detective who leads an elite unit in the crime thriller film "Den of Thieves."
  • E. Greg O’Connor
    Greg O’Connor is a film producer known for his work on crime and drama features, including the 2008 police drama "Pride and Glory."
  • 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_69d8e8db5b6c8190984b61f91981f575 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e638750b288190aecdb0e18a1add62 completed April 20, 2026, 2:30 p.m.
Created at: April 10, 2026, 1:41 p.m.