Triple

T22938534
Position Surface form Disambiguated ID Type / Status
Subject Nancy Walker E569653 entity
Predicate spouse P13 FINISHED
Object David Craig 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: David Craig | Statement: [Nancy Walker, spouse, David Craig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Craig
Context triple: [Nancy Walker, spouse, David Craig]
  • A. David Craig
    David Craig is a senior Royal Air Force officer who rose to become Chief of the Air Staff and later Chief of the Defence Staff of the United Kingdom.
  • B. David Craig chosen
    David Craig was the husband of American actress, comedian, and director Nancy Walker.
  • C. Dugald Macfadyen
    Dugald Macfadyen was a British Congregational minister, author, and biographer known for his religious writings and historical works in the late 19th and early 20th centuries.
  • D. Mark Strong
    Mark Strong is a British actor known for his intense screen presence and frequent roles as complex villains or stern mentors in films such as "Kingsman," "Sherlock Holmes," and "Tinker Tailor Soldier Spy."
  • E. Stephen Norton
    Stephen Norton is a mathematician known for his contributions to the theory of finite groups and the Monster group in particular.
  • 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_69e24590862c8190858f180ad302adab completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181378660819083239986c846ec17 completed April 29, 2026, 3:55 a.m.
Created at: April 17, 2026, 3:45 p.m.