Triple

T21297202
Position Surface form Disambiguated ID Type / Status
Subject James Warburg E524954 entity
Predicate spouse P13 FINISHED
Object Kay Swift 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: Kay Swift | Statement: [James Warburg, spouse, Kay Swift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kay Swift
Context triple: [James Warburg, spouse, Kay Swift]
  • A. Kay Swift chosen
    Kay Swift was an American composer and pianist best known as one of the first prominent female composers on Broadway and for her popular songs in the early 20th century.
  • B. Kay Medford
    Kay Medford was an American stage and screen actress best known for her Tony- and Oscar-nominated portrayal of Fanny Brice’s mother in the musical and film "Funny Girl."
  • C. Molly Cochran
    Molly Cochran is an American author best known for her fantasy and suspense novels, often blending historical elements with the supernatural.
  • D. Bree Schaaf
    Bree Schaaf is an American bobsledder who competed internationally for the United States, including at the Olympic level.
  • E. Victoria Kheel
    Victoria Kheel is an American set decorator and former spouse of actor James Spader.
  • 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_69e0b517e6748190850d6f6ddf323d69 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7385968308190bc9fe5c2bd4598e6 completed April 21, 2026, 8:42 a.m.
Created at: April 16, 2026, 4:04 p.m.