Triple

T13510160
Position Surface form Disambiguated ID Type / Status
Subject Contact E321116 entity
Predicate castMember P1668 FINISHED
Object Jay Leno E13481 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: Jay Leno | Statement: [Contact, castMember, Jay Leno]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jay Leno
Context triple: [Contact, castMember, Jay Leno]
  • A. Jay Leno chosen
    Jay Leno is an American comedian and longtime host of NBC’s “The Tonight Show,” known for his observational stand-up and prominent role in late-night television.
  • B. Mark Leno
    Mark Leno is an American Democratic politician and former California state legislator known for representing San Francisco in both the State Assembly and State Senate.
  • C. Leno
    Leno is a river in northern Italy that serves as a tributary of the Brenta River.
  • D. John Carson
    John Carson is a fictional character appearing in the film "The Miracle Woman."
  • E. Ed McMahon
    Ed McMahon was an American television personality and announcer best known as Johnny Carson’s longtime sidekick on “The Tonight Show.”
  • 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_69d807629d6c8190998f1b9bb12d2ed0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbaf86a6208190be8c18f7a0158f23 completed April 12, 2026, 2:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75490291c8190b5985d8c90ef1af6 completed May 3, 2026, 1:58 p.m.
Created at: April 9, 2026, 9:43 p.m.