Triple

T10260959
Position Surface form Disambiguated ID Type / Status
Subject Muhammad Ali vs Sonny Liston fight E240591 entity
Predicate judge P3169 FINISHED
Object Ruby Goldstein
Ruby Goldstein was a prominent American boxing referee and former fighter known for officiating major bouts in the mid-20th century.
E878521 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: Ruby Goldstein | Statement: [Muhammad Ali vs Sonny Liston fight, judge, Ruby Goldstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruby Goldstein
Context triple: [Muhammad Ali vs Sonny Liston fight, judge, Ruby Goldstein]
  • A. Rachel Leibowitz
    Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
  • B. Sara Goldfarb
    Sara Goldfarb is a lonely, television-obsessed Brooklyn widow whose descent into amphetamine addiction and delusion forms one of the central tragic arcs of "Requiem for a Dream."
  • C. Linda Goldstein
    Linda Goldstein is a music producer known for her work on projects such as the album "Simple Pleasures."
  • D. Jan Goldstein
    Jan Goldstein is an American novelist and inspirational speaker known for uplifting, emotionally driven fiction and motivational works.
  • E. Leslie Greif
    Leslie Greif is an American television producer and director best known for creating and producing popular series and miniseries across action, drama, and true-crime genres.
  • 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: Ruby Goldstein
Triple: [Muhammad Ali vs Sonny Liston fight, judge, Ruby Goldstein]
Generated description
Ruby Goldstein was a prominent American boxing referee and former fighter known for officiating major bouts in the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ruby Goldstein
Target entity description: Ruby Goldstein was a prominent American boxing referee and former fighter known for officiating major bouts in the mid-20th century.
  • A. Rachel Leibowitz
    Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
  • B. Sara Goldfarb
    Sara Goldfarb is a lonely, television-obsessed Brooklyn widow whose descent into amphetamine addiction and delusion forms one of the central tragic arcs of "Requiem for a Dream."
  • C. Linda Goldstein
    Linda Goldstein is a music producer known for her work on projects such as the album "Simple Pleasures."
  • D. Jan Goldstein
    Jan Goldstein is an American novelist and inspirational speaker known for uplifting, emotionally driven fiction and motivational works.
  • E. Leslie Greif
    Leslie Greif is an American television producer and director best known for creating and producing popular series and miniseries across action, drama, and true-crime genres.
  • 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_69d381a7e198819090280d5ab885d59e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d25bc7f88190b7e83243894d1aeb completed April 7, 2026, 9:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69d98811fd3881909369e0f00f2a8267 completed April 10, 2026, 11:30 p.m.
NEDg Description generation batch_69d98bf7a070819097b41b5018ef21f9 completed April 10, 2026, 11:47 p.m.
NED2 Entity disambiguation (via description) batch_69d98c5d0d088190bbcf08b3b5b14b49 completed April 10, 2026, 11:48 p.m.
Created at: April 6, 2026, 11:32 a.m.