Triple

T17752573
Position Surface form Disambiguated ID Type / Status
Subject Gleason’s theorem E443148 entity
Predicate author P4 FINISHED
Object Andrew M. Gleason 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: Andrew M. Gleason | Statement: [Gleason’s theorem, author, Andrew M. Gleason]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew M. Gleason
Context triple: [Gleason’s theorem, author, Andrew M. Gleason]
  • A. Andrew M. Gleason chosen
    Andrew M. Gleason was an American mathematician known for his influential work in measure theory, Hilbert’s fifth problem, and the foundations of quantum mechanics.
  • B. Herbert Edelman
    Herbert Edelman was an American character actor best known for his Emmy-nominated role as Stan Zbornak on the television sitcom "The Golden Girls."
  • C. George Gleason
    George Gleason is an American banker best known as the longtime chairman and CEO of Bank OZK, which he transformed from a small Arkansas bank into a major regional financial institution.
  • D. Leonard B. Loeb
    Leonard B. Loeb was an American physicist known for his work in ionized gases and electrical discharges, and for mentoring notable students such as Norris Bradbury.
  • E. George Kassabaum
    George Kassabaum was an American architect and co-founder of the global design and architecture firm HOK.
  • 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_69d8b9edf16c8190a59ebd245d378f4f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4841c0540819093a32d759775c61f completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.