Triple
T14423501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Khronos Group |
E357639
|
entity |
| Predicate | standard |
P1587
|
FINISHED |
| Object | SYCL |
E653476
|
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: SYCL | Statement: [Khronos Group, standard, SYCL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SYCL Context triple: [Khronos Group, standard, SYCL]
-
A.
SYCL
chosen
SYCL is a C++-based, cross-platform abstraction layer for heterogeneous parallel programming, designed to enable single-source development for CPUs, GPUs, and other accelerators.
-
B.
OpenCL
OpenCL is an open, cross-platform framework for writing programs that execute across heterogeneous systems including CPUs, GPUs, and other processors.
-
C.
OpenCL 2.2
OpenCL 2.2 is a version of the OpenCL standard that enhances heterogeneous parallel programming with features like improved kernel language support and better integration with modern C++-based compute models.
-
D.
OpenCL 2.0
OpenCL 2.0 is a version of the open standard parallel programming framework that enables heterogeneous computing across CPUs, GPUs, and other processors with features like shared virtual memory and improved kernel execution models.
-
E.
Intel oneAPI Toolkits
Intel oneAPI Toolkits are a collection of cross-architecture development tools from Intel designed to optimize and accelerate applications across CPUs, GPUs, and other accelerators.
- 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.