Triple

T9251193
Position Surface form Disambiguated ID Type / Status
Subject Lord Lieutenant of Kent E222325 entity
Predicate notableOfficeHolder P5750 FINISHED
Object Allan Willett E785720 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: Allan Willett | Statement: [Lord Lieutenant of Kent, notableOfficeHolder, Allan Willett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Allan Willett
Context triple: [Lord Lieutenant of Kent, notableOfficeHolder, Allan Willett]
  • A. Allan Willett chosen
    Allan Willett is a notable individual recognized for his prominence associated with the Willett surname.
  • B. John Willett
    John Willett is a notable individual distinguished enough to be recognized as a prominent bearer of the surname Willett.
  • C. Allan Little
    Allan Little is a British journalist and former BBC correspondent known for his in-depth reporting on international conflicts and political affairs.
  • D. Edward Willett
    Edward Willett is a Canadian science fiction and fantasy author known for novels such as "Marseguro" and for hosting "The Worldshapers" podcast.
  • E. Allan Pugh
    Allan Pugh is an individual notable enough to be specifically recorded as a bearer of the surname Pugh.
  • 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_69ca841d2b18819089f9faf5b2c2aec0 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd05f9ade48190ac8425a1c6f066b1 completed April 1, 2026, 11:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69d139b350e08190a68f8870433f6bae completed April 4, 2026, 4:17 p.m.
Created at: March 30, 2026, 7:31 p.m.