Triple

T15973339
Position Surface form Disambiguated ID Type / Status
Subject Jimmy Kimmel E387376 entity
Predicate coHostWith P5275 FINISHED
Object Adam Carolla E539810 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: Adam Carolla | Statement: [Jimmy Kimmel, coHostWith, Adam Carolla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adam Carolla
Context triple: [Jimmy Kimmel, coHostWith, Adam Carolla]
  • A. Adam Carolla chosen
    Adam Carolla is an American comedian, radio personality, podcaster, and actor best known for co-hosting "The Man Show" and creating "The Adam Carolla Show" podcast.
  • B. Dan Bilzerian
    Dan Bilzerian is an American social media personality, professional poker player, and businessman known for his lavish lifestyle and frequent appearances in action films.
  • C. Steve Harvey
    Steve Harvey is an American comedian, television host, and author best known for hosting shows like Family Feud and writing the relationship advice book "Act Like a Lady, Think Like a Man."
  • D. Howard Cannon
    Howard Cannon is a computer scientist and entrepreneur best known as one of the founders of the pioneering artificial intelligence company Symbolics.
  • E. Steve Ross
    Steve Ross was an American businessman best known for building Warner Communications into a media powerhouse and serving as a key architect of what became Time Warner.
  • 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_69d86da94ccc819083d187f5dc6a123e completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1572a8fd8819092ae1766324b1345 completed April 16, 2026, 9:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffbe8afa288190838cb35b8a4fcf50 completed May 9, 2026, 11:08 p.m.
Created at: April 10, 2026, 4:54 a.m.