Triple
T425476
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple M2 |
E8197
|
entity |
| Predicate | neuralEnginePerformance |
P13751
|
FINISHED |
| Object | 15.8 trillion operations per second |
—
|
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: 15.8 trillion operations per second | Statement: [Apple M2, neuralEnginePerformance, 15.8 trillion operations per second]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: neuralEnginePerformance Context triple: [Apple M2, neuralEnginePerformance, 15.8 trillion operations per second]
-
A.
neuralEngineType
Indicates the specific kind or category of neural processing engine associated with or used by an entity.
-
B.
integratesNeuralEngine
Indicates that one entity incorporates or embeds a neural processing engine within its overall system or architecture.
-
C.
performanceCores
Indicates a relationship where certain cores within a processor are designated as high-performance cores optimized for speed and intensive tasks.
-
D.
cpu
Indicates that an entity functions as, contains, or is associated with a central processing unit (CPU) in a computational system.
-
E.
gpuType
Indicates the specific kind or model category of GPU associated with an entity.
- F. None of above. chosen
Provenance (4 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_69a2e7f1d1bc81909cf2dc9754a3c334 |
completed | Feb. 28, 2026, 1:04 p.m. |
| NER | Named-entity recognition | batch_69a2eed56ab481909eec289075496260 |
completed | Feb. 28, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69a2edd6736c81909a6ca549f77b4345 |
completed | Feb. 28, 2026, 1:29 p.m. |
| PDg | Predicate description generation | batch_69a2eeb93584819082f23eff13e17c4f |
completed | Feb. 28, 2026, 1:33 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.