Triple

T21074624
Position Surface form Disambiguated ID Type / Status
Subject John Boulting E519197 entity
Predicate spouse P13 FINISHED
Object Enid Boulting 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: Enid Boulting | Statement: [John Boulting, spouse, Enid Boulting]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Enid Boulting
Context triple: [John Boulting, spouse, Enid Boulting]
  • A. Dilys Watling
    Dilys Watling was an English actress known for her work in television, film, and theatre, including appearances in British comedies and West End productions.
  • B. Jacqueline Boulting chosen
    Jacqueline Boulting was the wife of British film director and producer John Boulting, associated with the mid-20th-century British cinema scene.
  • C. Dilys Winn
    Dilys Winn was an influential American mystery bookseller and editor, best known for founding the first bookstore devoted exclusively to mystery fiction and for her contributions to popularizing the genre.
  • D. Louise Whitfield
    Louise Whitfield was an American philanthropist best known as the wife of industrialist Andrew Carnegie and for her extensive charitable work.
  • E. Dilys Thomas
    Dilys Thomas was the mother of British broadcaster and historian Jonathan Dimbleby.
  • 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_69e0b506e59c8190849b71ed07929215 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e702d5ae908190ab5303e39443d729 completed April 21, 2026, 4:53 a.m.
Created at: April 16, 2026, 2:48 p.m.