Triple

T17752449
Position Surface form Disambiguated ID Type / Status
Subject SU(2) E443145 entity
Predicate hasDynkinType P78097 FINISHED
Object A1 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: A1 | Statement: [SU(2), hasDynkinType, A1]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasDynkinType
Context triple: [SU(2), hasDynkinType, A1]
  • A. hasDynkinDiagram chosen
    Indicates that an algebraic or Lie-theoretic structure is associated with a specific Dynkin diagram that encodes its root system or classification.
  • B. hasCoxeterDiagram
    Indicates that an abstract Coxeter group or system is associated with a specific Coxeter diagram that encodes its generating reflections and their relations.
  • C. isCoxeterGroup
    Indicates that the given group satisfies the defining relations of a Coxeter group, i.e., it is generated by reflections with relations of the form \((s_is_j)^{m_{ij}} = e\) for specified integers \(m_{ij}\).
  • D. hasCoxeterPresentation
    Indicates that a group or structure is defined or characterized by a Coxeter presentation, i.e., by generators subject to relations determined by a Coxeter matrix or Coxeter diagram.
  • E. hasLieAlgebraDimension
    Indicates that an algebraic structure is associated with a Lie algebra having a specified vector-space dimension.
  • 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_69d8b9edf16c8190a59ebd245d378f4f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4841b3ccc8190b3241b3e0fa4b2e8 completed April 19, 2026, 7:28 a.m.
PD Predicate disambiguation batch_69e3cde9dc288190af0e2198487f2051 completed April 18, 2026, 6:31 p.m.
Created at: April 10, 2026, 10:10 a.m.