Triple

T5335945
Position Surface form Disambiguated ID Type / Status
Subject EATCS Award E123825 entity
Predicate notableRecipient P108 FINISHED
Object Dexter Kozen E239160 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: Dexter Kozen | Statement: [EATCS Award, notableRecipient, Dexter Kozen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dexter Kozen
Context triple: [EATCS Award, notableRecipient, Dexter Kozen]
  • A. Dexter Kozen chosen
    Dexter Kozen is an American theoretical computer scientist known for his influential work in logic in computer science, automata theory, and the semantics of programming languages.
  • B. Andrew G. Myers
    Andrew G. Myers is an American organic chemist renowned for his contributions to complex molecule synthesis and medicinal chemistry.
  • C. Robert Scheifler
    Robert Scheifler is a computer scientist best known for leading the development of the X Window System at MIT.
  • D. Michael Lehmann
    Michael Lehmann is an American film and television director best known for the dark comedy "Heathers" and various other Hollywood comedies.
  • E. Gerard J. Holzmann
    Gerard J. Holzmann is a computer scientist best known for creating the SPIN model checker and for his influential work in formal verification and software reliability.
  • 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_69bd464b07f8819095aa76577c9829e4 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85af799081909ee60bfbb65149ee completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21c20364819093387aa0e60b4291 completed March 21, 2026, 10:54 p.m.
Created at: March 20, 2026, 2 p.m.