Triple

T21892053
Position Surface form Disambiguated ID Type / Status
Subject Kim Delaney E540576 entity
Predicate spouse P13 FINISHED
Object Charles Grant 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: Charles Grant | Statement: [Kim Delaney, spouse, Charles Grant]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Charles Grant
Context triple: [Kim Delaney, spouse, Charles Grant]
  • A. Charles Grant
    Charles Grant was a prominent British politician and evangelical reformer associated with the Clapham Sect, known for his influential role in the East India Company and support for social and religious reforms.
  • B. Charles Grant chosen
    Charles Grant is a British football executive best known for serving as chairman of Crewe Alexandra F.C.
  • C. James Grant
    James Grant was a British Army general who played a leading role in several major engagements of the American Revolutionary War.
  • D. James Grant
    James Grant was a prominent American humanitarian and longtime executive director of UNICEF, renowned for his global efforts to improve child health and survival.
  • E. William Millar
    William Millar, better known by his stage name Stephen Boyd, was a Northern Irish-born actor famed for his role as Messala in the 1959 epic film "Ben-Hur."
  • 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_69e0c47a95908190ae3e19b716accb3d completed April 16, 2026, 11:14 a.m.
NER Named-entity recognition batch_69f11fc3727c8190b4d5d5a44aa2e55e completed April 28, 2026, 8:59 p.m.
Created at: April 16, 2026, 7:06 p.m.