Triple

T17872040
Position Surface form Disambiguated ID Type / Status
Subject Henkin construction E446858 entity
Predicate yields P490 FINISHED
Object Henkin model 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: Henkin model | Statement: [Henkin construction, yields, Henkin model]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Henkin model
Context triple: [Henkin construction, yields, Henkin model]
  • A. Henkin construction chosen
    Henkin construction is a model-building technique in first-order logic that extends a theory with new constants to ensure every consistent set of sentences has a model, thereby proving completeness.
  • B. organon model of language
    The organon model of language is a linguistic theory that explains language as a multifunctional tool for expressing thoughts, conveying information, and influencing others within a communicative context.
  • C. Henkin
    Henkin is a surname most notably associated with Leon Henkin, an influential logician known for his work in the foundations of mathematics and completeness in first-order logic.
  • D. Tucker model
    The Tucker model is a form of higher-order principal component analysis that decomposes a tensor into a core tensor multiplied by factor matrices along each mode, widely used for multi-way data analysis.
  • E. Fitting semantics for modal logic
    Fitting semantics for modal logic is a framework in mathematical logic that extends Kripke-style semantics to provide a more general and often intuitionistic treatment of modal operators.
  • 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_69d8b9f4c22c819093c2680434472894 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49aa30ff8819090c51c1d7767e952 completed April 19, 2026, 9:04 a.m.
Created at: April 10, 2026, 10:18 a.m.