Triple

T20105932
Position Surface form Disambiguated ID Type / Status
Subject Keith Larsen E490177 entity
Predicate name P16 FINISHED
Object Keith Larsen NE NERFINISHED

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: Keith Larsen | Statement: [Keith Larsen, name, Keith Larsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Keith Larsen
Context triple: [Keith Larsen, name, Keith Larsen]
  • A. Keith Larsen chosen
    Keith Larsen was an American actor best known for his roles in 1950s Western films and television series.
  • B. Michael Larsen
    Michael Larsen is the person credited with coining the now-popular term “Painted Ladies” to describe the colorfully restored Victorian and Edwardian houses of San Francisco.
  • C. Jonathan Larsen
    Jonathan Larsen is a New Zealand local government politician who serves as the deputy mayor of the Kaipara District.
  • D. William Larsen
    William Larsen is a songwriter best known for co-writing the hit country-pop song "H.O.L.Y." performed by Florida Georgia Line.
  • E. Neal Larson
    Neal Larson is a paleontologist and fossil dealer best known for co-founding the Black Hills Institute of Geological Research, a leading private organization in fossil excavation and preparation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69da62636cc08190982cc71733a17b8d completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e666dbad30819082454f360f358131 completed April 20, 2026, 5:48 p.m.
Created at: April 11, 2026, 11:28 p.m.