Triple

T13119143
Position Surface form Disambiguated ID Type / Status
Subject Split E311677 entity
Predicate character P662 FINISHED
Object Casey Cooke E311683 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: Casey Cooke | Statement: [Split, character, Casey Cooke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Casey Cooke
Context triple: [Split, character, Casey Cooke]
  • A. Casey Cooke chosen
    Casey Cooke is the resilient, traumatized teenage girl who serves as the central survivor and emotional core of M. Night Shyamalan’s thriller films "Split" and "Glass."
  • B. Casey Wescott
    Casey Wescott is an American musician best known as the keyboardist and multi-instrumentalist for the indie folk band Fleet Foxes.
  • C. Casey Stoney
    Casey Stoney is a former England international defender who has become a prominent women's football manager, known for her successful coaching roles in top-level clubs.
  • D. Casey Robinson
    Casey Robinson was an American screenwriter best known for his work on classic Hollywood films of the 1930s and 1940s, including several celebrated Errol Flynn swashbucklers and romantic dramas.
  • E. Casey Davenport
    Casey Davenport is a character from the animated series "Wings," likely serving as one of the show's central or recurring figures.
  • 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_69d806a9fe888190b081e2d9ea665d6c completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98196e69081909111407ee3d9f08e completed April 10, 2026, 11:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6e284c3c881909d65e2ba89fbe7af completed May 3, 2026, 5:52 a.m.
Created at: April 9, 2026, 9:06 p.m.