Triple

T23263083
Position Surface form Disambiguated ID Type / Status
Subject Kell Kelly E582063 entity
Predicate sibling P363 FINISHED
Object Elizabeth Kelly 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: Elizabeth Kelly | Statement: [Kell Kelly, sibling, Elizabeth Kelly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth Kelly
Context triple: [Kell Kelly, sibling, Elizabeth Kelly]
  • A. Elizabeth Kelly chosen
    Elizabeth Kelly was one of the sisters of American actress and Princess of Monaco Grace Kelly, belonging to the prominent Kelly family of Philadelphia.
  • B. Molly Murphy
    Molly Murphy is a character in the heist film "Finding Steve McQueen," involved in the story surrounding a notorious 1970s bank robbery.
  • C. Mary O'Leary
    Mary O'Leary is a notable individual distinguished enough to be specifically recognized as a prominent bearer of the O'Leary surname.
  • D. Mary Cleary
    Mary Cleary was the wife of Commodore John Barry, an early U.S. naval officer often called the "Father of the American Navy."
  • E. Katherine Parnell
    Katherine Parnell was a 19th-century Irishwoman best known as the sister of British Army officer and Victoria Cross recipient Sir Evelyn Wood.
  • 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_69e246079f58819085eaa9c260906880 completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f194caaf208190931923744692180d completed April 29, 2026, 5:19 a.m.
Created at: April 17, 2026, 4:11 p.m.