Triple

T19423651
Position Surface form Disambiguated ID Type / Status
Subject Dawn Moore E485923 entity
Predicate spouse P13 FINISHED
Object Wes Moore 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: Wes Moore | Statement: [Dawn Moore, spouse, Wes Moore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wes Moore
Context triple: [Dawn Moore, spouse, Wes Moore]
  • A. Wes Moore chosen
    Wes Moore is an American politician, author, and former nonprofit executive who became the first Black governor of Maryland.
  • B. Jelani Kilpatrick
    Jelani Kilpatrick is known as one of the sons of former Detroit mayor Kwame Kilpatrick.
  • C. Wyatt Tee Walker
    Wyatt Tee Walker was an influential American civil rights leader, close aide to Martin Luther King Jr., and chief strategist and organizer for the Southern Christian Leadership Conference.
  • D. Nicholas Lamont
    Nicholas Lamont is an actor known for his role in the British television series "Pie in the Sky."
  • E. J. D. Vance
    J. D. Vance is an American politician and author, known for his memoir "Hillbilly Elegy" and for serving as a Republican U.S. Senator from Ohio.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e632169d9c81909a88704c6beb8fe0 completed April 20, 2026, 2:03 p.m.
Created at: April 10, 2026, 1:37 p.m.