Triple
T9675013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NVIDIA Triton Inference Server |
E234124
|
entity |
| Predicate | supportsBatching |
P86209
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [NVIDIA Triton Inference Server, supportsBatching, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsBatching Context triple: [NVIDIA Triton Inference Server, supportsBatching, true]
-
A.
supportsBatchProcessing
chosen
Indicates that the subject can handle multiple items or tasks in a single grouped operation rather than processing them individually.
-
B.
supportsBatchScheduler
Indicates that an entity provides functionality or compatibility for executing tasks via a batch scheduling system.
-
C.
supportsMultipleStreams
Indicates that the subject is capable of handling or maintaining more than one data or communication stream at the same time.
-
D.
supportsTransactions
Indicates that one entity provides the capability for another entity to perform or manage transactions reliably.
-
E.
supportsRateLimiting
Indicates that one entity provides or is compatible with mechanisms to restrict the rate at which another entity can perform actions or process requests.
- 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_69ca848f55e48190b3f67252571c3d45 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9c6d6dd48190a77c486337a58cb6 |
completed | April 1, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69ccd5b5d40c8190850ad7a351445f32 |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:15 p.m.