Triple

T37411019
Position Surface form Disambiguated ID Type / Status
Subject Gelfand–Tsetlin algebra E929568 entity
Predicate actsDiagonallyOn P188046 FINISHED
Object Gelfand–Tsetlin basis 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: Gelfand–Tsetlin basis | Statement: [Gelfand–Tsetlin algebra, actsDiagonallyOn, Gelfand–Tsetlin basis]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: actsDiagonallyOn
Context triple: [Gelfand–Tsetlin algebra, actsDiagonallyOn, Gelfand–Tsetlin basis]
  • A. runsDiagonally
    Indicates that one entity extends or moves in a diagonal direction relative to another reference frame or axis.
  • B. diagonalRepresents
    Indicates that a diagonal in a figure or matrix stands for, encodes, or symbolizes a particular value, property, or relationship.
  • C. diagonalProperty
    Indicates a relationship where something possesses or exhibits a diagonal characteristic, alignment, or behavior relative to a reference frame or structure.
  • D. diagonalCondition
    Indicates that a specified relationship or constraint holds between elements positioned along a diagonal (such as in a matrix, grid, or board).
  • E. diagonalCount
    Indicates the number of diagonals associated with or present in a given object, structure, or configuration.
  • F. None of above. chosen

Provenance (4 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_69f76ebde49481908566cd96b37ccc84 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fb9e1845e881908d19158440cf3b87 completed May 6, 2026, 8:01 p.m.
PD Predicate disambiguation batch_69fb8d08d6988190a00794ac26078348 completed May 6, 2026, 6:48 p.m.
PDg Predicate description generation batch_69fb9e173f348190b7ab5935e4dca039 completed May 6, 2026, 8:01 p.m.
Created at: May 3, 2026, 4:16 p.m.