Triple

T20100691
Position Surface form Disambiguated ID Type / Status
Subject Elihu Yale E496526 entity
Predicate spouse P13 FINISHED
Object Catherine Hynmers 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: Catherine Hynmers | Statement: [Elihu Yale, spouse, Catherine Hynmers]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Catherine Hynmers
Context triple: [Elihu Yale, spouse, Catherine Hynmers]
  • A. Catherine Hynmers chosen
    Catherine Hynmers was the wife of Elihu Yale, the British-American merchant and philanthropist after whom Yale University is named.
  • B. Catherine Rowley
    Catherine Rowley was an English gentlewoman best known as the mother of Catherine Wellesley, Duchess of Wellington, and thus connected to one of Britain’s most prominent aristocratic and military families.
  • C. Catherine Moleyns
    Catherine Moleyns was an English noblewoman of the late medieval period, best known as the wife of John Howard, 1st Duke of Norfolk.
  • D. Catherine Morgan
    Catherine Morgan was the wife of American politician and Union Army general John Adams Dix, known primarily for her role within his prominent 19th-century political and military household.
  • E. Catherine Gwatkin
    Catherine Gwatkin was the wife of British poet and literary critic Lascelles Abercrombie.
  • 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_69da626eee3881909f3454986d4a6511 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6666ff4008190ae1eec907c89bd3b completed April 20, 2026, 5:46 p.m.
Created at: April 11, 2026, 11:26 p.m.