Triple

T22484325
Position Surface form Disambiguated ID Type / Status
Subject Mike Gordon E555841 entity
Predicate associatedAct P37 FINISHED
Object Leo Kottke 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: Leo Kottke | Statement: [Mike Gordon, associatedAct, Leo Kottke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leo Kottke
Context triple: [Mike Gordon, associatedAct, Leo Kottke]
  • A. Leo Kottke chosen
    Leo Kottke is an American acoustic guitarist renowned for his virtuosic fingerpicking style and genre-blending instrumental compositions.
  • B. Daniel Kottke
    Daniel Kottke is an early Apple employee and close college friend of Steve Jobs who worked on the original Apple computers.
  • C. Chris Smither
    Chris Smither is an American folk and blues singer-songwriter and guitarist known for his intricate fingerpicking style and introspective, lyrically rich songs.
  • D. Michael Hedges
    Michael Hedges was an innovative American acoustic guitarist and composer known for his groundbreaking percussive fingerstyle technique and influential recordings in the new-age and contemporary instrumental genres.
  • E. Owen Strand
    Owen Strand is a fictional New York firefighter captain who relocates to Austin, Texas to rebuild a firehouse and lead its diverse crew in the TV series "9-1-1: Lone Star."
  • 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_69e11e53897c819088863779f8c50bb0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15c3bb8cc8190950efd84ebe86b73 completed April 29, 2026, 1:17 a.m.
Created at: April 16, 2026, 8:49 p.m.