Triple

T7416905
Position Surface form Disambiguated ID Type / Status
Subject Mike and Mike E171151 entity
Predicate presenter P83 FINISHED
Object Mike Golic E664032 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: Mike Golic | Statement: [Mike and Mike, presenter, Mike Golic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mike Golic
Context triple: [Mike and Mike, presenter, Mike Golic]
  • A. Mike Golic chosen
    Mike Golic is a former NFL defensive lineman and longtime ESPN radio personality best known for co-hosting the popular sports talk show "Mike and Mike."
  • B. Lorne David Michaels
    Lorne David Michaels is a Canadian-American television producer, writer, and comedian best known as the creator and longtime executive producer of the sketch comedy show Saturday Night Live.
  • C. Lou Carducci
    Lou Carducci is a fictional character played by American actress and model Mackenzie Foy.
  • D. Chris Berman
    Chris Berman is a longtime ESPN sportscaster best known for his energetic NFL coverage and signature catchphrases.
  • E. Gus Johnson
    Gus Johnson was an American jazz drummer known for his swinging style and work with prominent big bands and blues musicians in the mid-20th century.
  • 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_69c68a618bdc81908d8018edadecd1a4 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f2c7ae0c8190a8348d6223aeeecc completed March 27, 2026, 9:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8277c92788190bcd36cfa461b4d95 completed March 28, 2026, 7:09 p.m.
Created at: March 27, 2026, 3:11 p.m.