Triple

T19714323
Position Surface form Disambiguated ID Type / Status
Subject King Kong (stage musical) E473432 entity
Predicate lyricsBy P1141 FINISHED
Object Craig Lucas 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: Craig Lucas | Statement: [King Kong (stage musical), lyricsBy, Craig Lucas]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig Lucas
Context triple: [King Kong (stage musical), lyricsBy, Craig Lucas]
  • A. Craig Lucas chosen
    Craig Lucas is an American playwright, screenwriter, and director known for his work on stage and film, particularly in exploring complex emotional and social themes.
  • B. Ben Lucas
    Ben Lucas is a central character in the psychological thriller novel "Before I Go to Sleep," serving as the protagonist Christine's husband and a key figure in the mystery surrounding her amnesia.
  • C. Charlie Lucas
    Charlie Lucas is an actor known for his role in the film "Tea with Mussolini."
  • D. Nicholas Lucas
    Nicholas Lucas was an early colonial leader known for helping establish the West Jersey settlement in what is now New Jersey.
  • E. Steve Lacey
    Steve Lacey is the protagonist of the 1954 film noir "Crime Wave," a reformed ex-convict struggling to escape his criminal past when former associates draw him back into a web of crime.
  • 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6440b47508190a8a33325b00841dc completed April 20, 2026, 3:19 p.m.
Created at: April 10, 2026, 1:46 p.m.