Triple
T36184736
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arnold cat map |
E1046813
|
entity |
| Predicate | hasMatrixRepresentation |
P204100
|
FINISHED |
| Object | [[2,1],[1,1]] modulo 1 |
—
|
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: [[2,1],[1,1]] modulo 1 | Statement: [Arnold cat map, hasMatrixRepresentation, [[2,1],[1,1]] modulo 1]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMatrixRepresentation Context triple: [Arnold cat map, hasMatrixRepresentation, [[2,1],[1,1]] modulo 1]
-
A.
hasMatrixType
Indicates that an entity is associated with or characterized by a specific type or category of matrix.
-
B.
hasAdjointRepresentation
Indicates that a mathematical object (typically a Lie group or Lie algebra) is associated with its adjoint representation, describing how it acts on its own Lie algebra via the adjoint action.
-
C.
hasMatrixOperations
Indicates that an entity supports or provides functionality for performing matrix-related operations.
-
D.
hasRandomMatrixForm
Indicates that one entity can be represented or expressed in the form of a random matrix associated with another entity.
-
E.
hasMatrixNumber
Indicates that an entity is associated with a specific matrix identification number used to uniquely reference it.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a03232efd8481908ee25447a29ee20b |
completed | May 12, 2026, 12:55 p.m. |
| PD | Predicate disambiguation | batch_6a032269dcb08190907c965c28145b77 |
completed | May 12, 2026, 12:51 p.m. |
| PDg | Predicate description generation | batch_6a03232e53788190abf17396e8d02dbf |
completed | May 12, 2026, 12:55 p.m. |
Created at: May 3, 2026, 4:08 p.m.