Triple

T2596727
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl XXVII E58248 entity
Predicate referee P268 FINISHED
Object Dick Hantak
Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
E359542 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: Dick Hantak | Statement: [Super Bowl XXVII, referee, Dick Hantak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dick Hantak
Context triple: [Super Bowl XXVII, referee, Dick Hantak]
  • A. Ron Hagen
    Ron Hagen is a cinematographer best known for his work on the Australian film "Romper Stomper."
  • B. Jim Harrick
    Jim Harrick is an American college basketball coach best known for leading UCLA to the 1995 NCAA championship.
  • C. Ben Haggerty
    Ben Haggerty, better known by his stage name Macklemore, is an American rapper and songwriter recognized for hits like "Thrift Shop" and "Can't Hold Us."
  • D. Gary Waldhorn
    Gary Waldhorn was a British actor best known for his comedic and character roles on television and stage, particularly in popular UK sitcoms.
  • E. Jack Gariss
    Jack Gariss was an American screenwriter best known for his work on major mid-20th-century Hollywood films, including contributing to the script of Cecil B. DeMille’s epic "The Ten Commandments" (1956).
  • 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: Dick Hantak
Triple: [Super Bowl XXVII, referee, Dick Hantak]
Generated description
Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Dick Hantak
Target entity description: Dick Hantak is a former National Football League official best known for serving as the referee in Super Bowl XXVII.
  • A. Ron Hagen
    Ron Hagen is a cinematographer best known for his work on the Australian film "Romper Stomper."
  • B. Jim Harrick
    Jim Harrick is an American college basketball coach best known for leading UCLA to the 1995 NCAA championship.
  • C. Ben Haggerty
    Ben Haggerty, better known by his stage name Macklemore, is an American rapper and songwriter recognized for hits like "Thrift Shop" and "Can't Hold Us."
  • D. Gary Waldhorn
    Gary Waldhorn was a British actor best known for his comedic and character roles on television and stage, particularly in popular UK sitcoms.
  • E. Jack Gariss
    Jack Gariss was an American screenwriter best known for his work on major mid-20th-century Hollywood films, including contributing to the script of Cecil B. DeMille’s epic "The Ten Commandments" (1956).
  • 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_69ab4ac14040819098b13f4a27d5c8ff completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd42b3cd4819093b2cab78de1f66c completed March 7, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69b360793f908190b0341c003207cc6f completed March 13, 2026, 12:55 a.m.
NEDg Description generation batch_69b3614702348190bd35c37d2059312f completed March 13, 2026, 12:58 a.m.
NED2 Entity disambiguation (via description) batch_69b362451b848190a2fe80a17ab8f9c3 completed March 13, 2026, 1:03 a.m.
Created at: March 6, 2026, 9:49 p.m.