Triple

T9360126
Position Surface form Disambiguated ID Type / Status
Subject Mark Leno E225255 entity
Predicate familyName P18 FINISHED
Object Leno E225255 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: Leno | Statement: [Mark Leno, familyName, Leno]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leno
Context triple: [Mark Leno, familyName, Leno]
  • A. Mark Leno chosen
    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.
  • B. Jay Leno
    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.
  • C. Chevy Chase
    Chevy Chase is an American comedian and actor best known for his work on "Saturday Night Live" and the "National Lampoon's Vacation" film series.
  • D. Will Murray
    Will Murray is an American writer best known for his extensive work continuing classic pulp fiction series, particularly the Doc Savage novels.
  • E. David Letterman
    David Letterman is an American television host and comedian best known for his long-running late-night talk shows, including "Late Night with David Letterman" and "The Late Show with David Letterman."
  • 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_69ca842bdd648190904131d58620d448 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd4ff2ca9081908ccc88651640ed84 completed April 1, 2026, 5:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69d100d000a081909964736e8a7418ba completed April 4, 2026, 12:15 p.m.
Created at: March 30, 2026, 7:42 p.m.