Triple
T31025326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WMMA API |
E790552
|
entity |
| Predicate | targetHardwareFeature |
P118536
|
FINISHED |
| Object | Tensor Cores |
—
|
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: Tensor Cores | Statement: [WMMA API, targetHardwareFeature, Tensor Cores]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetHardwareFeature Context triple: [WMMA API, targetHardwareFeature, Tensor Cores]
-
A.
targetFeature
Indicates that one entity is the specific feature, attribute, or characteristic that another entity is directed toward, focused on, or intended to affect.
-
B.
hasHardwareCompatibilityWith
Indicates that two hardware components or systems can operate together correctly and reliably without conflicts or incompatibilities.
-
C.
targetPlatformFeature
chosen
Indicates that a particular feature is available on, or specifically associated with, a given target platform.
-
D.
hasHardware
Indicates that one entity possesses, includes, or is equipped with specific hardware components or devices.
-
E.
capabilityType
Indicates the type or category of capability that an entity possesses or is associated with.
- 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_69f224c811508190a7de096a5b1f5798 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fd76d1e5208190a6f26651492d1e3c |
completed | May 8, 2026, 5:38 a.m. |
| PD | Predicate disambiguation | batch_69fd702a226c81908edfda00f4be4130 |
completed | May 8, 2026, 5:10 a.m. |
Created at: April 29, 2026, 8:58 p.m.