Triple

T5406102
Position Surface form Disambiguated ID Type / Status
Subject Richard J. Riordan E120895 entity
Predicate precededBy P97 FINISHED
Object Tom Bradley E485851 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: Tom Bradley | Statement: [Richard J. Riordan, precededBy, Tom Bradley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Bradley
Context triple: [Richard J. Riordan, precededBy, Tom Bradley]
  • A. Tom Bradley chosen
    Tom Bradley was a long-serving and influential mayor of Los Angeles who played a key role in the city’s late-20th-century growth and international prominence.
  • B. Norman Chandler
    Norman Chandler was an American newspaper publisher who led the Los Angeles Times to major expansion and influence in the mid-20th century.
  • C. Coleman A. Young
    Coleman A. Young was a pioneering African American politician who served as the long-time mayor of Detroit, Michigan, from 1974 to 1994.
  • D. Willie Brown
    Willie Brown was a Hall of Fame NFL cornerback best known for his long tenure and three Super Bowl titles with the Oakland Raiders.
  • E. Pat Brown
    Pat Brown was a mid-20th-century Democratic politician who served as the 32nd governor of California and played a major role in expanding the state's infrastructure and higher education system.
  • 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_69bd46391c0c81909fa484446732b6a3 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd87924c588190beb4a1be27f8d11b completed March 20, 2026, 5:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf3394af9c81909f9a3bb06d48595d completed March 22, 2026, 12:11 a.m.
Created at: March 20, 2026, 2:05 p.m.