Triple

T10226645
Position Surface form Disambiguated ID Type / Status
Subject The Fifth Element E243221 entity
Predicate starredActor P5563 FINISHED
Object Luke Perry E293930 NE FINISHED

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: Luke Perry | Statement: [The Fifth Element, starredActor, Luke Perry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luke Perry
Context triple: [The Fifth Element, starredActor, Luke Perry]
  • A. Luke Perry chosen
    Luke Perry was an American actor best known for his role as Dylan McKay on the television series "Beverly Hills, 90210."
  • B. Kevin Judd
    Kevin Judd is a musician best known as a member of the American rock band Ultra Q.
  • C. Tim Reid
    Tim Reid is an American actor and comedian best known for his roles on television series such as "WKRP in Cincinnati," "Simon & Simon," and "Frank's Place."
  • D. Greg Reeves
    Greg Reeves is an American bass guitarist best known for playing with Crosby, Stills, Nash & Young, including on their landmark 1970 album "Déjà Vu."
  • E. Rich Little
    Rich Little is a Canadian-American impressionist and comedian renowned for his uncanny vocal impersonations of famous politicians and celebrities.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d381b0f97c819085c9b45799a5fb7c completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d1fa98a48190a5caf6b6003bc14c completed April 7, 2026, 9:44 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f71fb4048190a36f1fe499729332 completed April 9, 2026, 12:47 a.m.
Created at: April 6, 2026, 11:17 a.m.