Triple
T4276936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CuPy |
E97065
|
entity |
| Predicate | typicalSpeedup |
P55146
|
FINISHED |
| Object | faster than NumPy on compatible GPU workloads |
—
|
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: faster than NumPy on compatible GPU workloads | Statement: [CuPy, typicalSpeedup, faster than NumPy on compatible GPU workloads]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalSpeedup Context triple: [CuPy, typicalSpeedup, faster than NumPy on compatible GPU workloads]
-
A.
speed
Indicates the rate at which an entity moves or changes position over time.
-
B.
recommendedSpeed
Indicates the speed that is advised or suggested as appropriate under given conditions, rather than required or actual speed.
-
C.
speedAchieved
Indicates that a particular speed has been reached or attained by an entity during an event or action.
-
D.
migrationSpeed
Indicates the rate at which an entity moves from one location or region to another over a given period of time.
-
E.
hasAverageSurfaceSpeed
Indicates the typical or mean speed at which something moves across a surface over a given period or distance.
- 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_69b34544be3c819084d1ab82d29f90c5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3501d677481909e7416a1d2b0008c |
completed | March 12, 2026, 11:45 p.m. |
| PD | Predicate disambiguation | batch_69b347faa45481908c19c29fb906dc92 |
completed | March 12, 2026, 11:10 p.m. |
| PDg | Predicate description generation | batch_69b34e0606488190baadf469a1afc3c2 |
completed | March 12, 2026, 11:36 p.m. |
Created at: March 12, 2026, 11:07 p.m.