Triple
T26378356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intelligence Processing Unit |
E660957
|
entity |
| Predicate | hardwareParadigm |
P76305
|
FINISHED |
| Object | manycore architecture |
—
|
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: manycore architecture | Statement: [Intelligence Processing Unit, hardwareParadigm, manycore architecture]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hardwareParadigm Context triple: [Intelligence Processing Unit, hardwareParadigm, manycore architecture]
-
A.
graphicsArchitecture
Indicates the underlying design or structural framework that defines how a system’s graphics or visual rendering components are organized and operate.
-
B.
hardwarePlatformFor
Indicates that one entity serves as the hardware platform on which another entity is designed to run or be deployed.
-
C.
hardwareUsed
Indicates that a particular piece of hardware is utilized or employed in performing an action, process, or function involving another entity.
-
D.
hardwareCategory
chosen
Indicates that an item belongs to or is classified under a specific hardware category or type.
-
E.
hardwareComponent
Indicates that one entity is a physical hardware part or module that is contained in, attached to, or functionally part of another hardware system or device.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f61072d5f481908ef99900df8d23e7 |
completed | May 2, 2026, 2:55 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 26, 2026, 11:03 p.m.