Triple
T31909370
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ONNX Runtime |
E814638
|
entity |
| Predicate | supportsExecutionProvider |
—
|
GENERATED |
| Object | CUDA |
—
|
UNRECOGNIZED GENERATED |
How this triple was built (1 step)
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.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsExecutionProvider Context triple: [ONNX Runtime, supportsExecutionProvider, CUDA]
-
A.
supportsNeuralNetworkAcceleration
Indicates that one entity provides hardware or software capabilities that enhance the speed or efficiency of neural network computations for another entity.
-
B.
supportsQuantization
Indicates that one entity is capable of operating with, or is compatible with, quantized representations or computations of another entity.
-
C.
supportsGPUType
chosen
Indicates that one entity is compatible with, or capable of operating using, a specified type of GPU.
-
D.
supportsPretrainedModels
Indicates that an entity provides compatibility with or functionality for using pretrained models.
-
E.
neuralEngineType
Indicates the specific kind or category of neural processing engine associated with or used by an entity.
- F. None of above.
Provenance (1 batch)
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_69f348f109d88190b5005372c53d2fcd |
completed | April 30, 2026, 12:20 p.m. |
Created at: May 1, 2026, 12:01 a.m.