Triple
T27682369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jacobi eigenvalue algorithm |
E697940
|
entity |
| Predicate | matrixClass |
P133839
|
FINISHED |
| Object | normal matrices (via unitary version) |
—
|
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: normal matrices (via unitary version) | Statement: [Jacobi eigenvalue algorithm, matrixClass, normal matrices (via unitary version)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: matrixClass Context triple: [Jacobi eigenvalue algorithm, matrixClass, normal matrices (via unitary version)]
-
A.
mathematicalClassification
chosen
Indicates that one entity is categorized or identified according to a particular mathematical type, structure, or property defined by another entity.
-
B.
hasMatrixOperations
Indicates that an entity supports or provides functionality for performing matrix-related operations.
-
C.
numberOfIndependentMatrices
Indicates the count of matrices in a set that are linearly independent from each other.
-
D.
matrixMaterial
Indicates that one material serves as the continuous matrix phase in which another component or reinforcement is embedded.
-
E.
hasMatrixType
Indicates that an entity is associated with or characterized by a specific type or category of matrix.
- 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_69ef590df8708190af5488f0638e790c |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63538f2388190919cba716e850b5b |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:47 p.m.