Triple
T7279604
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AMD Radeon integrated graphics |
E163112
|
entity |
| Predicate | supports |
P516
|
FINISHED |
| Object | Vulkan |
E163107
|
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: Vulkan | Statement: [AMD Radeon integrated graphics, supports, Vulkan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vulkan Context triple: [AMD Radeon integrated graphics, supports, Vulkan]
-
A.
Vulkan
chosen
Vulkan is a low-overhead, cross-platform 3D graphics and compute API designed to provide high-performance access to modern GPUs.
-
B.
Direct3D 12
Direct3D 12 is a low-level graphics API from Microsoft that provides high-performance, close-to-the-metal access to GPU hardware for Windows and Xbox game and graphics development.
-
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.
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.
-
E.
WebGPU
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.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb339b1081909f648864e210f98e |
completed | March 27, 2026, 8:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7e532a7f08190a5c0b1167dc0be44 |
completed | March 28, 2026, 2:26 p.m. |
Created at: March 27, 2026, 2:59 p.m.