Triple

T15829328
Position Surface form Disambiguated ID Type / Status
Subject President of UEA E383827 entity
Predicate officeHolder P537 FINISHED
Object Duncan Charters E313673 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: Duncan Charters | Statement: [President of UEA, officeHolder, Duncan Charters]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Duncan Charters
Context triple: [President of UEA, officeHolder, Duncan Charters]
  • A. Duncan Charters chosen
    Duncan Charters is an educator and linguist best known for his leadership role in the international Esperanto movement.
  • B. Hal Caine
    Hal Caine is a fictional character known primarily as the husband of Charly Baltimore in the film "The Long Kiss Goodnight."
  • C. Sherwood Morgan
    Sherwood Morgan was the husband of civil rights figure Irene Morgan, known for her landmark role in challenging segregation laws in the United States.
  • D. Tim Crompton
    Tim Crompton is a collegiate sports administrator who serves as the athletic director overseeing Weber State University's athletics program, including its football team.
  • E. Woody Kaine
    Woody Kaine is one of the children of American politicians Tim Kaine and Anne Holton, known primarily as a member of their family rather than for a public career of his own.
  • 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_69d86da34c888190976e06c4019d415a completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e11e62aba8819090978801f4df73fe completed April 16, 2026, 5:37 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff999f9ccc8190bc859c2b78a16baf completed May 9, 2026, 8:31 p.m.
Created at: April 10, 2026, 4:49 a.m.