Triple

T10149634
Position Surface form Disambiguated ID Type / Status
Subject Ellen Gleason E232596 entity
Predicate relativeOf P367 FINISHED
Object Kate Gleason E31446 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: Kate Gleason | Statement: [Ellen Gleason, relativeOf, Kate Gleason]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kate Gleason
Context triple: [Ellen Gleason, relativeOf, Kate Gleason]
  • A. Kate Gleason chosen
    Kate Gleason was a pioneering American engineer and businesswoman, recognized as one of the first female mechanical engineers and a trailblazer for women in the engineering profession.
  • B. Al Smith
    Al Smith was an American politician and four-term New York governor who became the first Roman Catholic major-party nominee for U.S. president in 1928.
  • C. Thomas J. Gleason
    Thomas J. Gleason is an American politician who served as a member of the Massachusetts House of Representatives.
  • D. Robert Daley
    Robert Daley is an American film producer best known for his longtime collaboration with Clint Eastwood on numerous movies throughout the 1970s and 1980s.
  • E. Robert Daley
    Robert Daley is best known as the father of British Olympic diver Tom Daley.
  • 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_69ca84885e48819088a31b127cf44904 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdec03e80c81909c813dae91c56272 completed April 2, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69d2e6369c848190984394eedf2f07eb completed April 5, 2026, 10:46 p.m.
Created at: March 30, 2026, 9:08 p.m.