Triple

T23062713
Position Surface form Disambiguated ID Type / Status
Subject Nyad E574945 entity
Predicate portraysRealPerson P10301 FINISHED
Object Diana Nyad 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: Diana Nyad | Statement: [Nyad, portraysRealPerson, Diana Nyad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Diana Nyad
Context triple: [Nyad, portraysRealPerson, Diana Nyad]
  • A. Diana Nyad chosen
    Diana Nyad is an American long-distance swimmer and journalist best known for her record-setting, non-stop swim from Cuba to Florida at age 64.
  • B. Nyad
    Nyad is a biographical drama film depicting long-distance swimmer Diana Nyad's historic attempt to swim from Cuba to Florida at age 64.
  • C. Gertrude Ederle
    Gertrude Ederle was an American competitive swimmer who became the first woman to swim across the English Channel, breaking the existing men's record in 1926.
  • D. Ellen MacArthur
    Ellen MacArthur is a British yachtswoman famed for breaking the world record for the fastest solo circumnavigation of the globe and for her later leadership in promoting the circular economy.
  • E. Suzanne Coston
    Suzanne Coston is a television producer best known for her executive production work on the series "Beggars and Choosers."
  • 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_69e245bd6e4c8190bb8942245b68cad5 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f189a0c3c881909f137ad511c216ac completed April 29, 2026, 4:31 a.m.
Created at: April 17, 2026, 3:55 p.m.