Triple
T31025352
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WMMA API |
E790552
|
entity |
| Predicate | programmingModelLevel |
P107164
|
FINISHED |
| Object | device-level API |
—
|
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: device-level API | Statement: [WMMA API, programmingModelLevel, device-level API]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: programmingModelLevel Context triple: [WMMA API, programmingModelLevel, device-level API]
-
A.
hasProgrammingModel
chosen
Indicates that one entity defines, specifies, or is associated with the programming model used or supported by another entity.
-
B.
architectureLevel
Indicates the relative layer or tier an entity occupies within an architectural structure or system design.
-
C.
softwareModel
Indicates that one entity serves as a software-based representation or abstraction (a model) of another entity or system.
-
D.
programLevel
Indicates the hierarchical or categorical level at which a program is defined or operates (e.g., undergraduate, graduate, or other tiers).
-
E.
developmentModelFor
Indicates that one entity serves as the development model, framework, or paradigm used to guide or structure the creation or evolution of another entity.
- 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_69f6e6029a10819098ff21f58079e70e |
completed | May 3, 2026, 6:06 a.m. |
| PD | Predicate disambiguation | batch_69f6e3d5e8188190b1e1c2e5d1b77031 |
completed | May 3, 2026, 5:57 a.m. |
Created at: April 29, 2026, 8:58 p.m.