Triple

T2815708
Position Surface form Disambiguated ID Type / Status
Subject Why I Love Baseball E54279 entity
Predicate mainSubject P3 FINISHED
Object Larry King E194734 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: Larry King | Statement: [Why I Love Baseball, mainSubject, Larry King]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Larry King
Context triple: [Why I Love Baseball, mainSubject, Larry King]
  • A. Larry King chosen
    Larry King is an American attorney and promoter best known as the former husband and early manager of tennis legend Billie Jean King.
  • B. Larry King
    Larry King was a legendary American television and radio host best known for his long-running CNN interview show "Larry King Live," where he spoke with world leaders, celebrities, and newsmakers.
  • C. Mike Wallace
    Mike Wallace was a prominent American broadcast journalist best known as a hard-hitting correspondent on the television news magazine "60 Minutes."
  • D. Matt Lauer
    Matt Lauer is an American television journalist and former longtime co-host of NBC's "Today" show.
  • E. David Brinkley
    David Brinkley was a prominent American television newscaster and journalist best known for co-anchoring "The Huntley–Brinkley Report" and later serving as a leading figure in network evening news.
  • 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_69ab49de0af08190b3da69683be1e728 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde4ed4ac81909f1ec4a3f7869bc1 completed March 7, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69b261cda3ac8190b8770e554a66f560 completed March 12, 2026, 6:48 a.m.
Created at: March 6, 2026, 9:59 p.m.