Triple

T22974024
Position Surface form Disambiguated ID Type / Status
Subject Storks E571263 entity
Predicate voiceCast P18510 FINISHED
Object Ty Burrell 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: Ty Burrell | Statement: [Storks, voiceCast, Ty Burrell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ty Burrell
Context triple: [Storks, voiceCast, Ty Burrell]
  • A. Ty Burrell chosen
    Ty Burrell is an American actor and comedian best known for his Emmy-winning role as Phil Dunphy on the television series "Modern Family."
  • B. Joe Morton
    Joe Morton is an American actor known for his versatile film and television roles, including notable performances in projects like "Terminator 2: Judgment Day" and the TV series "Scandal."
  • C. John Izard
    John Izard was an American statesman from South Carolina who served as a delegate to the Continental Congress during the Revolutionary era.
  • D. Leslie Jordan
    Leslie Jordan was an Emmy-winning American actor and comedian known for his distinctive Southern charm and scene-stealing roles in television, film, and theater.
  • E. Chris Givens
    Chris Givens is a former American football wide receiver who played college football at Wake Forest University before moving on to a professional career in the NFL.
  • 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_69e245b2c6548190a0e4c7f2f7df2d48 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f182350b448190a34e5fa0167fd964 completed April 29, 2026, 3:59 a.m.
Created at: April 17, 2026, 3:48 p.m.