Triple

T8823363
Position Surface form Disambiguated ID Type / Status
Subject CUDA Fortran E209956 entity
Predicate supports P516 FINISHED
Object cuFFT
cuFFT is NVIDIA's GPU-accelerated Fast Fourier Transform library designed to perform high-performance FFT computations on CUDA-enabled devices.
 E758503 NE FINISHED

How this triple was built (4 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 Fortran, supports, cuFFT]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: cuFFT
Context triple: [CUDA Fortran, supports, cuFFT]
  • A. 3 CFFTS
    3 CFFTS is a Royal Canadian Air Force training unit responsible for advanced flying instruction and pilot development in Canada.
  • B. 2 CFFTS
    2 CFFTS is a Royal Canadian Air Force training unit responsible for providing pilot and aircrew flying instruction in Canada.
  • C. FFT
    FFT is the ICAO airline designator used in aviation to identify Frontier Airlines in flight plans and air traffic control communications.
  • D. FFT
    FFT is the French Tennis Federation, the national governing body for tennis in France and organizer of major tournaments including the French Open.
  • E. cuBLAS
    cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: cuFFT
Triple: [CUDA Fortran, supports, cuFFT]
Generated description
cuFFT is NVIDIA's GPU-accelerated Fast Fourier Transform library designed to perform high-performance FFT computations on CUDA-enabled devices.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: cuFFT
Target entity description: cuFFT is NVIDIA's GPU-accelerated Fast Fourier Transform library designed to perform high-performance FFT computations on CUDA-enabled devices.
  • A. 3 CFFTS
    3 CFFTS is a Royal Canadian Air Force training unit responsible for advanced flying instruction and pilot development in Canada.
  • B. 2 CFFTS
    2 CFFTS is a Royal Canadian Air Force training unit responsible for providing pilot and aircrew flying instruction in Canada.
  • C. FFT
    FFT is the ICAO airline designator used in aviation to identify Frontier Airlines in flight plans and air traffic control communications.
  • D. FFT
    FFT is the French Tennis Federation, the national governing body for tennis in France and organizer of major tournaments including the French Open.
  • E. cuBLAS
    cuBLAS is NVIDIA’s GPU-accelerated implementation of the BLAS linear algebra library, providing high-performance matrix and vector operations for CUDA applications.
  • F. None of above. chosen

Provenance (5 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_69cf6fd3b3348190a63bfd29860cc95f completed April 3, 2026, 7:44 a.m.
NEDg Description generation batch_69cf70ca613c8190bcebec47f8cdfc55 completed April 3, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_69cf7235c954819096a51e75f2fb6240 completed April 3, 2026, 7:54 a.m.
Created at: March 30, 2026, 6:46 p.m.