Triple

T17035322
Position Surface form Disambiguated ID Type / Status
Subject Tucker decomposition E413306 entity
Predicate optimizationFormulation P3660 FINISHED
Object least-squares minimization LITERAL 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: least-squares minimization | Statement: [Tucker decomposition, optimizationFormulation, least-squares minimization]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: optimizationFormulation
Context triple: [Tucker decomposition, optimizationFormulation, least-squares minimization]
  • A. exampleFormulation
    Indicates that one entity serves as a representative or illustrative formulation or expression of another entity.
  • B. optimizationSolver
    Indicates a relationship where a solver entity is used to compute an optimal solution for a given optimization problem or task.
  • C. mathematicallyFormulatedIn
    Indicates that something is expressed, defined, or represented using mathematical formulas, equations, or formal mathematical structures within a given context.
  • D. hasEquivalentFormulation
    Indicates that two representations, statements, or formulations express the same underlying meaning, condition, or effect, even if they differ in form.
  • E. hasFormulation chosen
    Indicates that one entity is expressed, prepared, or configured in a particular form or composition defined by another entity.
  • F. None of above.

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_69d886cd18288190b006abab23f811b7 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d8f05824819091d2aa02e5591e26 completed April 18, 2026, 7:18 p.m.
PD Predicate disambiguation batch_69e35d5be7f48190af9db67a1e23850f completed April 18, 2026, 10:30 a.m.
Created at: April 10, 2026, 5:33 a.m.