Triple

T19244002
Position Surface form Disambiguated ID Type / Status
Subject 1958 NBA All-Star Game E481200 entity
Predicate televisionAnnouncer P7529 FINISHED
Object Marty Glickman NE NERFINISHED

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: Marty Glickman | Statement: [1958 NBA All-Star Game, televisionAnnouncer, Marty Glickman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marty Glickman
Context triple: [1958 NBA All-Star Game, televisionAnnouncer, Marty Glickman]
  • A. Marty Glickman chosen
    Marty Glickman was an American sprinter and pioneering sportscaster best known for his track career and influential broadcasting work in professional basketball and football.
  • B. John Froines
    John Froines was an American chemist, anti–Vietnam War activist, and one of the defendants in the infamous Chicago Seven trial.
  • C. Mort Briskin
    Mort Briskin was a screenwriter known for his work on mid-20th-century American films, including the crime drama "A Man Alone."
  • D. Jac Holzman
    Jac Holzman is an American music industry executive best known as the founder of Elektra Records and a pioneering figure in the development of the modern record label.
  • E. Glenn Berger
    Glenn Berger is an American screenwriter best known for co-writing major animated films such as the Kung Fu Panda series.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5faf47820819081e8b6af852bb1dd completed April 20, 2026, 10:07 a.m.
Created at: April 10, 2026, 1:27 p.m.