Triple

T9298147
Position Surface form Disambiguated ID Type / Status
Subject Tensor Cores E223691 entity
Predicate exposedThrough P87910 FINISHED
Object CUDA E41922 NE FINISHED

How this triple was built (3 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: CUDA | Statement: [Tensor Cores, exposedThrough, CUDA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CUDA
Context triple: [Tensor Cores, exposedThrough, CUDA]
  • A. NVIDIA CUDA chosen
    NVIDIA CUDA is a parallel computing platform and programming model that enables developers to use NVIDIA GPUs for general-purpose high-performance computing.
  • B. CUDA libraries
    CUDA libraries are a collection of NVIDIA-provided GPU-accelerated software libraries that offer optimized routines for tasks such as linear algebra, deep learning, signal processing, and parallel algorithms on CUDA-enabled hardware.
  • C. GPU
    The GPU (State Political Directorate) was the Soviet Union’s early secret police and intelligence agency that operated in the 1920s, overseeing political repression and internal security before later reorganizations.
  • D. GPU
    GPU is the vehicle registration code used on license plates for cars registered in Poland’s Pomeranian Voivodeship.
  • E. GPU
    A GPU (Graphics Processing Unit) is a highly parallel processor originally designed for rendering graphics that is now widely used to accelerate compute-intensive tasks such as machine learning, scientific simulations, and video processing.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: exposedThrough
Context triple: [Tensor Cores, exposedThrough, CUDA]
  • A. exposedAs
    Indicates that one entity reveals or publicly identifies another entity as having a hidden, false, or previously concealed role, identity, or nature.
  • B. exposesTo
    Indicates that one entity subjects another entity to contact with or influence from something, typically involving risk, effect, or experience.
  • C. exposed
    Indicates that one entity has been made visible, revealed, or left unprotected to another entity or to some external influence.
  • D. exposedDuring
    Indicates that something becomes visible, accessible, or subject to influence specifically within a given time period, event, or contextual interval.
  • E. exposes
    Indicates making something visible, known, or vulnerable by removing cover, concealment, or protection.
  • 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_69ca8423edb08190bc0c91287a484768 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd089e3ae88190aa4181cdd85a67b8 completed April 1, 2026, 11:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69d0b251c4148190a94fafdc23a601d6 completed April 4, 2026, 6:40 a.m.
PD Predicate disambiguation batch_69cc7a5ef1908190bc5ca166bb895af6 completed April 1, 2026, 1:52 a.m.
PDg Predicate description generation batch_69cc95597be081908ece2491dd2f0f74 completed April 1, 2026, 3:47 a.m.
Created at: March 30, 2026, 7:36 p.m.