Triple

T22094624
Position Surface form Disambiguated ID Type / Status
Subject City of Joy E545992 entity
Predicate stars P1956 FINISHED
Object Patrick Swayze 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: Patrick Swayze | Statement: [City of Joy, stars, Patrick Swayze]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patrick Swayze
Context triple: [City of Joy, stars, Patrick Swayze]
  • A. Patrick Swayze chosen
    Patrick Swayze was an American actor and dancer best known for his charismatic leading roles in hit films such as "Dirty Dancing" and "Ghost."
  • B. Tom Swayze
    Tom Swayze was a notable figure in American college baseball, best known as a long-time and highly successful head coach at the University of Mississippi.
  • C. Don Swayze
    Don Swayze is an American character actor known for his work in film and television, often appearing in supporting and guest roles across various dramas and action series.
  • D. Jesse Wayne Swayze
    Jesse Wayne Swayze was the father of American actor and dancer Patrick Swayze.
  • E. John Travolta
    John Travolta is an American actor, singer, and producer known for iconic roles in films such as "Saturday Night Fever," "Grease," and "Pulp Fiction."
  • 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_69e11e36d03c8190a83a1ba802b7231b completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128e82c1481908701f255b834f192 completed April 28, 2026, 9:38 p.m.
Created at: April 16, 2026, 8:29 p.m.