Triple
T14423624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | WebGPU |
E357641
|
entity |
| Predicate | exposes |
P25434
|
FINISHED |
| Object | GPUComputePassEncoder interface |
E357641
|
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: GPUComputePassEncoder interface | Statement: [WebGPU, exposes, GPUComputePassEncoder interface]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GPUComputePassEncoder interface Context triple: [WebGPU, exposes, GPUComputePassEncoder interface]
-
A.
WebGPU
chosen
WebGPU is a modern web graphics and compute API designed to provide high-performance, low-level access to GPU capabilities in browsers, succeeding and improving upon WebGL.
-
B.
GPUOpen
GPUOpen is AMD's open-source initiative and developer portal that provides tools, libraries, and resources for graphics and game development on Radeon GPUs.
-
C.
SPIR-V
SPIR-V is a standardized intermediate binary language for representing shaders and compute kernels, primarily used in the Vulkan graphics and compute API ecosystem.
-
D.
CUDA-like API
A CUDA-like API is a programming interface that closely mirrors NVIDIA's CUDA model, enabling developers to write GPU-accelerated code that can be more easily ported across different hardware platforms.
-
E.
NVIDIA OptiX
NVIDIA OptiX is a GPU-accelerated, programmable ray tracing engine and API from NVIDIA used to build high-performance, photorealistic rendering and simulation applications.
- 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_69d82793421c8190861eb0e673b085de |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91123f848190ba3fb18a76c2d24c |
completed | April 14, 2026, 7:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bcd2a908190ad7d5ebf11b41551 |
completed | May 8, 2026, 3:43 a.m. |
Created at: April 10, 2026, 1:18 a.m.