Triple

T23234937
Position Surface form Disambiguated ID Type / Status
Subject orthogonal group O(n+1,2) E581259 entity
Predicate hasCartanDecomposition P73433 FINISHED
Object 𝔰𝔬(n+1,2)=π”¨βŠ•π”­ β€” LITERAL FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order β€” 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: 𝔰𝔬(n+1,2)=π”¨βŠ•π”­ | Statement: [orthogonal group O(n+1,2), hasCartanDecomposition, 𝔰𝔬(n+1,2)=π”¨βŠ•π”­]
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasCartanDecomposition
Context triple: [orthogonal group O(n+1,2), hasCartanDecomposition, 𝔰𝔬(n+1,2)=π”¨βŠ•π”­]
  • A. hasCartanSubalgebraDimension
    Indicates that an algebraic or Lie algebraic structure has a Cartan subalgebra whose dimension equals a specified value.
  • B. hasCanonicalDecomposition
    Indicates that an entity can be expressed as a standard or normalized combination of more basic components or parts.
  • C. hasDecomposition chosen
    Indicates that something can be broken down or separated into constituent parts, components, or simpler elements.
  • D. hasCanonicalBasis
    Indicates that there exists a standard or preferred basis associated with an entity, typically used as the reference basis in its context.
  • E. hasLieAlgebra
    Indicates that one mathematical structure is associated with, or gives rise to, a specific Lie algebra capturing its infinitesimal or tangent-level structure.
  • F. None of above.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level β€” stages were processed in waves, so the object chain (NER β†’ NED1 β†’ NEDg β†’ NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69e2460556f88190be1744a84a84173f completed April 17, 2026, 2:39 p.m.
NER Named-entity recognition batch_69f192e8c7548190b53434eeb2620a6e completed April 29, 2026, 5:11 a.m.
PD Predicate disambiguation batch_69effcdadec0819092ec1749ee453b4e completed April 28, 2026, 12:18 a.m.
Created at: April 17, 2026, 4:09 p.m.