Triple

T12164534
Position Surface form Disambiguated ID Type / Status
Subject George Villiers, 2nd Duke of Buckingham E289795 entity
Predicate spouse P13 FINISHED
Object Mary Fairfax E112022 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: Mary Fairfax | Statement: [George Villiers, 2nd Duke of Buckingham, spouse, Mary Fairfax]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Fairfax
Context triple: [George Villiers, 2nd Duke of Buckingham, spouse, Mary Fairfax]
  • A. Mary Fairfax chosen
    Mary Fairfax was the daughter of English Civil War general Sir Thomas Fairfax, belonging to the prominent Fairfax noble family of 17th-century England.
  • B. Mary Fairfax
    Mary Fairfax, later known as Mary Somerville, was a pioneering 19th-century Scottish mathematician and science writer whose work helped popularize and advance mathematical and astronomical knowledge.
  • C. Mary Hudson
    Mary Hudson is an American Christian pastor and author best known as the mother of pop singer Katy Perry.
  • D. Daisy Barlow
    Daisy Barlow is a daughter of English singer-songwriter and Take That frontman Gary Barlow.
  • E. Mary Jane Grant
    Mary Jane Grant is best known as the former wife of American actor Richard Roundtree, famed for his iconic role as detective John Shaft in the "Shaft" film series.
  • 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_69d6ab4d6c00819095a9a7c35de83cfb completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915c498a081908389598d0c247505 completed April 10, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f6a2716081909620a9d11cfcc2d8 completed May 2, 2026, 1:05 p.m.
Created at: April 8, 2026, 9:50 p.m.