Triple

T8310053
Position Surface form Disambiguated ID Type / Status
Subject Horace Mann Bond E194567 entity
Predicate child P120 FINISHED
Object Julian Bond E33681 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: Julian Bond | Statement: [Horace Mann Bond, child, Julian Bond]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Julian Bond
Context triple: [Horace Mann Bond, child, Julian Bond]
  • A. Julian Bond
    Julian Bond is a British screenwriter best known for his work on the period drama film "The Shooting Party."
  • B. Julian Bond chosen
    Julian Bond was a prominent American civil rights leader, politician, and educator who co-founded the Student Nonviolent Coordinating Committee and later chaired the NAACP.
  • C. James Farmer
    James Farmer was a prominent American civil rights leader and co-founder of the Congress of Racial Equality (CORE), known for organizing the Freedom Rides to challenge segregation in the South.
  • D. John Hope Franklin
    John Hope Franklin was a pioneering American historian and civil rights advocate renowned for his groundbreaking scholarship on African American history and race in the United States.
  • E. Bob Moses
    Bob Moses was a prominent civil rights activist and organizer best known for his leadership in voter registration drives and grassroots education initiatives in the American South during the 1960s.
  • 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_69ca82e613e88190bf8139669bbd0d53 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f2d2c30819095075940479b75a7 completed March 31, 2026, 8 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd95665390819089c8becad018cf51 completed April 1, 2026, 10 p.m.
Created at: March 30, 2026, 5:54 p.m.