Triple
T1810356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple M1 Ultra |
E40316
|
entity |
| Predicate | UltraFusionBandwidth |
P1376
|
FINISHED |
| Object | 2.5 TB/s |
—
|
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: 2.5 TB/s | Statement: [Apple M1 Ultra, UltraFusionBandwidth, 2.5 TB/s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: UltraFusionBandwidth Context triple: [Apple M1 Ultra, UltraFusionBandwidth, 2.5 TB/s]
-
A.
usesChannelBandwidth
Indicates that one entity consumes or occupies a portion of the available bandwidth on a communication channel.
-
B.
dataRate
chosen
Indicates the rate at which data is transmitted, processed, or transferred between entities over a given time interval.
-
C.
multipleAccessSchemeUplink
Indicates that the uplink communication uses multiple access schemes to allow multiple users or signals to share the same transmission resources.
-
D.
dataRateGeneration
Indicates the rate at which data is produced or generated over time in a given context.
-
E.
maxSpatialStreams
Indicates the maximum number of simultaneous spatial data streams that can be used or supported in a communication or processing context.
- 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_69a88643a3388190a612f2ebe1fb29e7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab694d75ac8190a4d61399c04b9fb9 |
completed | March 6, 2026, 11:54 p.m. |
| PD | Predicate disambiguation | batch_69aa61d6b8ec8190a1597b2e44ea6534 |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:32 p.m.