Triple

T6331481
Position Surface form Disambiguated ID Type / Status
Subject Super Bowl XXIII E142390 entity
Predicate referee P268 FINISHED
Object Jerry Markbreit E245508 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: Jerry Markbreit | Statement: [Super Bowl XXIII, referee, Jerry Markbreit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jerry Markbreit
Context triple: [Super Bowl XXIII, referee, Jerry Markbreit]
  • A. Jerry Markbreit chosen
    Jerry Markbreit is a former National Football League official renowned as one of the league’s most prominent referees, working numerous high-profile games including multiple Super Bowls.
  • B. August Eberstein
    August Eberstein was a German engineer and entrepreneur best known as one of the original creators of the Montblanc luxury fountain pen brand in the early 20th century.
  • C. William Nack
    William Nack was an American sportswriter and author best known for his definitive biography of the racehorse Secretariat.
  • D. Frank Klingebiel
    Frank Klingebiel is a German local politician who serves as the long-time mayor of the city of Salzgitter in Lower Saxony.
  • E. William Gleason
    William Gleason was a member of the prominent Gleason family associated with American industrialist and engineer Kate Gleason.
  • 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06514cbe8819096dbeb17ccb3e3d5 completed March 22, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6041f713c8190b27ba54181049377 completed March 27, 2026, 4:14 a.m.
Created at: March 22, 2026, 4:30 p.m.