Triple

T7090402
Position Surface form Disambiguated ID Type / Status
Subject Brady E165176 entity
Predicate hasNotableBearer P458 FINISHED
Object James Brady E120550 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: James Brady | Statement: [Brady, hasNotableBearer, James Brady]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Brady
Context triple: [Brady, hasNotableBearer, James Brady]
  • A. James S. Brady chosen
    James S. Brady was the White House press secretary who was gravely wounded during the 1981 assassination attempt on President Ronald Reagan and later became a prominent advocate for gun control.
  • B. Thomas Hinckley
    Thomas Hinckley was a colonial American politician who served as the last governor of Plymouth Colony before its merger into the Province of Massachusetts Bay.
  • C. William Todd
    William Todd was the designer of the original Bear Flag that became the basis for the modern state flag of California.
  • D. John O'Neil
    John O'Neil is best known as the former husband of American actress Teri Garr.
  • E. John Allen
    John Allen was an American military officer and politician whose legacy includes having Allen County, Indiana, named in his honor.
  • 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_69c6887e8c10819091cee237560d32da completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6e53012b081908bf40541d85c82f1 completed March 27, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7948cb3d48190993134d709924e3d completed March 28, 2026, 8:42 a.m.
Created at: March 27, 2026, 2:41 p.m.