Triple

T11842520
Position Surface form Disambiguated ID Type / Status
Subject Ali (2001 film) E281687 entity
Predicate character P662 FINISHED
Object Drew Bundini Brown
Drew Bundini Brown was the charismatic and poetic cornerman and assistant trainer best known for his close association with boxing legend Muhammad Ali.
 E949188 NE FINISHED

How this triple was built (4 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: Drew Bundini Brown | Statement: [Ali (2001 film), character, Drew Bundini Brown]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Drew Bundini Brown
Context triple: [Ali (2001 film), character, Drew Bundini Brown]
  • A. Drew Brown
    Drew Brown is an American musician best known as the guitarist for the pop rock band OneRepublic.
  • B. Drew Brown
    Drew Brown is a writer known for contributing to the publication Good Life.
  • C. Addison Brown
    Addison Brown was an American jurist and amateur botanist known for co-authoring influential botanical works with Nathaniel Lord Britton.
  • D. Dartanyan Edmonds
    Dartanyan Edmonds is an American actor best known for his comedic roles in early-2000s films and television, including the romantic comedy "Deliver Us from Eva."
  • E. Drew Bagnell
    Drew Bagnell is a roboticist and machine learning researcher known for his work in autonomous systems and his role as a co-founder and chief scientist at Aurora Innovation.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Drew Bundini Brown
Triple: [Ali (2001 film), character, Drew Bundini Brown]
Generated description
Drew Bundini Brown was the charismatic and poetic cornerman and assistant trainer best known for his close association with boxing legend Muhammad Ali.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Drew Bundini Brown
Target entity description: Drew Bundini Brown was the charismatic and poetic cornerman and assistant trainer best known for his close association with boxing legend Muhammad Ali.
  • A. Drew Brown
    Drew Brown is an American musician best known as the guitarist for the pop rock band OneRepublic.
  • B. Drew Brown
    Drew Brown is a writer known for contributing to the publication Good Life.
  • C. Addison Brown
    Addison Brown was an American jurist and amateur botanist known for co-authoring influential botanical works with Nathaniel Lord Britton.
  • D. Dartanyan Edmonds
    Dartanyan Edmonds is an American actor best known for his comedic roles in early-2000s films and television, including the romantic comedy "Deliver Us from Eva."
  • E. Drew Bagnell
    Drew Bagnell is a roboticist and machine learning researcher known for his work in autonomous systems and his role as a co-founder and chief scientist at Aurora Innovation.
  • F. None of above. chosen

Provenance (5 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_69d6ab287ba48190a5178779fd19b9b7 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a65a597c8190b09f57463b279afc completed April 10, 2026, 7:27 a.m.
NED1 Entity disambiguation (via context triple) batch_69f1679729c08190a9f6750586f90d8d completed April 29, 2026, 2:06 a.m.
NEDg Description generation batch_69f17005c318819090e54bc64d135477 completed April 29, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_69f17814de1881908973af026af5d1d1 completed April 29, 2026, 3:16 a.m.
Created at: April 8, 2026, 9:43 p.m.