Triple

T13755567
Position Surface form Disambiguated ID Type / Status
Subject Jane Swift E330466 entity
Predicate name P16 FINISHED
Object Jane Swift E330466 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: Jane Swift | Statement: [Jane Swift, name, Jane Swift]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jane Swift
Context triple: [Jane Swift, name, Jane Swift]
  • A. Jane Swift chosen
    Jane Swift is an American politician who became the first woman to serve as governor of Massachusetts, holding the office from 2001 to 2003.
  • B. Rebecca Swift
    Rebecca Swift is a British poet, editor, and co-founder of The Literary Consultancy, known for her contributions to contemporary literature and support for emerging writers.
  • C. Elizabeth Kitley
    Elizabeth Kitley is an American college basketball center for Virginia Tech, recognized as one of the top players in the nation and a multi-time ACC Player of the Year.
  • D. Victoria Prentis
    Victoria Prentis is a British Conservative Party politician and government minister who has served as the Member of Parliament for Banbury since 2015.
  • E. Rosalind Hicks
    Rosalind Hicks was the only child of famed mystery writer Agatha Christie and the longtime guardian of her literary estate.
  • 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_69d81c573f288190aa2403d484fa3d49 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02179c948190a652cc8c586e418f completed April 14, 2026, 9 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7a859e6748190aa1899830a02b710 completed May 3, 2026, 7:56 p.m.
Created at: April 9, 2026, 10:09 p.m.