Triple
T25933334
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intel Gaussian and Neural Accelerator 2.0 |
E653485
|
entity |
| Predicate | targetWorkloadType |
P22769
|
FINISHED |
| Object | inference |
—
|
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: inference | Statement: [Intel Gaussian and Neural Accelerator 2.0, targetWorkloadType, inference]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetWorkloadType Context triple: [Intel Gaussian and Neural Accelerator 2.0, targetWorkloadType, inference]
-
A.
supportsWorkloadType
chosen
Indicates that one entity is capable of handling, operating with, or being compatible with a specified type of workload.
-
B.
targetWork
Indicates that one entity is the specific work (e.g., document, artwork, or project) that another entity is directed at, refers to, or is primarily concerned with.
-
C.
associatedWorkType
Indicates the type or category of work with which an entity is associated (e.g., publication, artwork, performance).
-
D.
targetFleetType
Indicates the specific category or classification of fleet that is the intended focus or recipient of an action or relationship.
-
E.
multipleWorkingType
Indicates that an entity is associated with more than one type of work or employment classification simultaneously.
- 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_69e7ab3eb9b881909c1390690551f868 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 22, 2026, 8:37 a.m.