Triple
T30421943
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IBM Gekko |
E773922
|
entity |
| Predicate | SIMDExtensions |
P74581
|
FINISHED |
| Object | custom SIMD instructions for graphics and media |
—
|
LITERAL 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: custom SIMD instructions for graphics and media | Statement: [IBM Gekko, SIMDExtensions, custom SIMD instructions for graphics and media]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SIMDExtensions Context triple: [IBM Gekko, SIMDExtensions, custom SIMD instructions for graphics and media]
-
A.
SIMDSupport
Indicates that an entity provides or is compatible with SIMD (Single Instruction, Multiple Data) operations or instruction sets.
-
B.
instructionSetExtensions
chosen
Indicates that one entity defines, supports, or includes additional instruction set features or extensions relative to another.
-
C.
supportsAVX
Indicates that one entity provides or is compatible with AVX (Advanced Vector Extensions) functionality for another entity or operation.
-
D.
supportsAVX2
Indicates that one entity provides or has compatibility with AVX2 (Advanced Vector Extensions 2) instruction set capabilities for another.
-
E.
supportsSuperscalarExecution
Indicates that an architecture or component can execute multiple instructions in parallel within a single clock cycle using superscalar techniques.
- F. None of above.
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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68663d49c81908c44b8cb0f31d014 |
completed | May 2, 2026, 11:19 p.m. |
| PD | Predicate disambiguation | batch_69f678d019fc8190913662cd2f87b857 |
completed | May 2, 2026, 10:21 p.m. |
Created at: April 29, 2026, 8:06 p.m.