Triple

T10942971
Position Surface form Disambiguated ID Type / Status
Subject Lisa Askey E258520 entity
Predicate relative P37 FINISHED
Object Kaya Faison E905354 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: Kaya Faison | Statement: [Lisa Askey, relative, Kaya Faison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaya Faison
Context triple: [Lisa Askey, relative, Kaya Faison]
  • A. Kaya Faison chosen
    Kaya Faison is one of the children of the late nurse Lisa Askey and actor Donald Faison.
  • B. Sarah Chalke
    Sarah Chalke is a Canadian actress best known for her roles as Dr. Elliot Reid on the sitcom "Scrubs" and Becky Conner on "Roseanne."
  • C. Kaitlin Olson
    Kaitlin Olson is an American actress and comedian best known for playing Dee Reynolds on the long-running sitcom "It's Always Sunny in Philadelphia."
  • D. Candice Accola
    Candice Accola is an American actress and singer best known for her role as Caroline Forbes on the television series "The Vampire Diaries."
  • E. Caity Lotz
    Caity Lotz is an American actress, dancer, and director best known for her role as Sara Lance/White Canary in the Arrowverse television series, particularly DC's Legends of Tomorrow.
  • 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_69d6aa8769b4819082bfe5e61b9017f0 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770c3fb388190a598f89ae59a7b51 completed April 9, 2026, 9:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69e4418e52f8819096c75e6e866fecef completed April 19, 2026, 2:44 a.m.
Created at: April 8, 2026, 9:23 p.m.