Triple

T15991033
Position Surface form Disambiguated ID Type / Status
Subject Balfour E387823 entity
Predicate hasNotableBearer P458 FINISHED
Object Evelyn Balfour E1181395 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: Evelyn Balfour | Statement: [Balfour, hasNotableBearer, Evelyn Balfour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Evelyn Balfour
Context triple: [Balfour, hasNotableBearer, Evelyn Balfour]
  • A. Evelyn Balfour chosen
    Evelyn Balfour was a member of the prominent British Balfour family, known primarily through her connection to Conservative politician James Maitland Balfour and the wider political dynasty that included Prime Minister Arthur Balfour.
  • B. Henrietta Tyrrell
    Henrietta Tyrrell was an artist linked to the early 20th-century British avant-garde Vorticist movement.
  • C. Leslie Cavendish
    Leslie Cavendish is the wife of British film producer Jonathan Cavendish, known for her connection to his work and public profile.
  • D. Evelyn Vernon
    Evelyn Vernon was the wife of American businessman and Johnson & Johnson leader Robert Wood Johnson II.
  • E. Maud Windsor
    Maud Windsor is a young member of the British royal family, the daughter of Lord Frederick Windsor and granddaughter of Prince and Princess Michael of Kent.
  • 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_69d86daa562c81908aacc179c0fe8fb5 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157835cac81909e979f9be281f328 completed April 16, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffe46f19f48190a33647c711893564 completed May 10, 2026, 1:50 a.m.
Created at: April 10, 2026, 4:54 a.m.