Triple
T29938265
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | cuSOLVER |
E760426
|
entity |
| Predicate | supportsSparseFormat |
P80839
|
FINISHED |
| Object | CSR format |
—
|
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: CSR format | Statement: [cuSOLVER, supportsSparseFormat, CSR format]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsSparseFormat Context triple: [cuSOLVER, supportsSparseFormat, CSR format]
-
A.
hasSparse
Indicates that one entity possesses or exhibits another entity in a thinly distributed, scattered, or low-density manner.
-
B.
supportsRowFormat
chosen
Indicates that one entity provides compatibility with or can correctly handle the specified row format of another entity.
-
C.
usesSparseInstrumentation
Indicates that an entity performs monitoring or data collection with minimal or selectively placed instrumentation rather than comprehensive coverage.
-
D.
defaultSparseFormatInJulia
Indicates that an entity is represented or output using Julia’s default sparse matrix formatting conventions.
-
E.
supportsCompressedFiles
Indicates that one entity is capable of handling, reading, or working with files that are stored in a compressed format.
- 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_69f22463f3648190a603c3ff305c660b |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 6:21 p.m.