Triple

T584485
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl III E15128 entity
Predicate referee P268 FINISHED
Object Tom Bell
Tom Bell was an American football official best known for serving as the referee in Super Bowl III.
 E97239 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: Tom Bell | Statement: [Super Bowl III, referee, Tom Bell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tom Bell
Context triple: [Super Bowl III, referee, Tom Bell]
  • A. Brian Bilello
    Brian Bilello is an American soccer executive best known for leading Major League Soccer’s New England Revolution as the club’s president.
  • B. David Gamble
    David Gamble is a film editor best known for his work on the Academy Award–winning romantic comedy-drama "Shakespeare in Love."
  • C. Curtis Stigers
    Curtis Stigers is an American jazz and soul-influenced singer, saxophonist, and songwriter known for his early 1990s pop hits and later critically acclaimed jazz recordings.
  • D. Don Maynard
    Don Maynard was a Hall of Fame American football wide receiver best known as Joe Namath’s primary deep threat and a key offensive star for the New York Jets during the 1960s.
  • E. Kim Carnes
    Kim Carnes is an American singer-songwriter best known for her raspy voice and the 1981 hit single "Bette Davis Eyes."
  • 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: Tom Bell
Triple: [Super Bowl III, referee, Tom Bell]
Generated description
Tom Bell was an American football official best known for serving as the referee in Super Bowl III.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tom Bell
Target entity description: Tom Bell was an American football official best known for serving as the referee in Super Bowl III.
  • A. Brian Bilello
    Brian Bilello is an American soccer executive best known for leading Major League Soccer’s New England Revolution as the club’s president.
  • B. David Gamble
    David Gamble is a film editor best known for his work on the Academy Award–winning romantic comedy-drama "Shakespeare in Love."
  • C. Curtis Stigers
    Curtis Stigers is an American jazz and soul-influenced singer, saxophonist, and songwriter known for his early 1990s pop hits and later critically acclaimed jazz recordings.
  • D. Don Maynard
    Don Maynard was a Hall of Fame American football wide receiver best known as Joe Namath’s primary deep threat and a key offensive star for the New York Jets during the 1960s.
  • E. Chuck Cecil
    Chuck Cecil is a former American football safety best known for his hard-hitting play in the NFL and his standout collegiate career at the University of Arizona.
  • 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_69a4935783b8819082b77726ec10cc42 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49b9874c88190bd1e08d4689ea124 completed March 1, 2026, 8:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d6571588190b1f328e7b10b627c completed March 3, 2026, 11:23 p.m.
NEDg Description generation batch_69a78ce2d3608190af4f38768b6ef95e completed March 4, 2026, 1:37 a.m.
NED2 Entity disambiguation (via description) batch_69a78d84ccd08190aaa86a0adbd993a0 completed March 4, 2026, 1:40 a.m.
Created at: March 1, 2026, 7:33 p.m.