Triple
T8823756
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CUDA |
E209963
|
entity |
| Predicate | includesLibrary |
P1393
|
FINISHED |
| Object | cuFFT |
E758503
|
NE 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: cuFFT | Statement: [CUDA, includesLibrary, cuFFT]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: cuFFT Context triple: [CUDA, includesLibrary, cuFFT]
-
A.
cuFFT
chosen
cuFFT is NVIDIA's GPU-accelerated Fast Fourier Transform library designed to perform high-performance FFT computations on CUDA-enabled devices.
-
B.
3 CFFTS
3 CFFTS is a Royal Canadian Air Force training unit responsible for advanced flying instruction and pilot development in Canada.
-
C.
2 CFFTS
2 CFFTS is a Royal Canadian Air Force training unit responsible for providing pilot and aircrew flying instruction in Canada.
-
D.
FFT
FFT is the ICAO airline designator used in aviation to identify Frontier Airlines in flight plans and air traffic control communications.
-
E.
FFT
FFT is the French Tennis Federation, the national governing body for tennis in France and organizer of major tournaments including the French Open.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca8364e13081909c85fe80f44fe86f |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc6030b25081909d67488b35a72e05 |
completed | April 1, 2026, midnight |
| NED1 | Entity disambiguation (via context triple) | batch_69cfa05742948190bcec72a080f6837a |
completed | April 3, 2026, 11:11 a.m. |
Created at: March 30, 2026, 6:46 p.m.