Triple

T20021270
Position Surface form Disambiguated ID Type / Status
Subject Ann Patricia Dowling E494863 entity
Predicate familyName P18 FINISHED
Object Dowling 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: Dowling | Statement: [Ann Patricia Dowling, familyName, Dowling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dowling
Context triple: [Ann Patricia Dowling, familyName, Dowling]
  • A. Dowling chosen
    Dowling is a surname of Irish origin borne by various notable individuals across fields such as sports, politics, and the arts.
  • B. Dahl-Wolfe
    Dahl-Wolfe is the surname of Louise Dahl-Wolfe, a pioneering American fashion photographer known for her influential work for Harper’s Bazaar in the mid-20th century.
  • C. Blondell
    Blondell is a surname most notably associated with American actress Joan Blondell, a popular film and stage star of the 1930s and 1940s.
  • D. Dully
    Dully is a small Swiss municipality located on the shores of Lake Geneva in the canton of Vaud.
  • E. Dowden
    Dowden is an English surname most notably associated in contemporary politics with British Conservative politician Oliver Dowden.
  • 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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6623fe1988190a1c09d392d866dc8 completed April 20, 2026, 5:28 p.m.
Created at: April 11, 2026, 3:35 p.m.