Triple
T30421979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gekko |
E773923
|
entity |
| Predicate | specializedInstructions |
P89239
|
FINISHED |
| Object | SIMD extensions for 3D graphics |
—
|
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: SIMD extensions for 3D graphics | Statement: [Gekko, specializedInstructions, SIMD extensions for 3D graphics]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: specializedInstructions Context triple: [Gekko, specializedInstructions, SIMD extensions for 3D graphics]
-
A.
branchSpecialization
Indicates that one branch or subdivision is specialized or focused in a particular area, function, or domain relative to others.
-
B.
exportSpecialization
Indicates a relationship where one entity specializes in exporting particular goods, services, or resources to another entity or market.
-
C.
isSpecializedFor
chosen
Indicates that one entity is specifically adapted, designed, or focused to perform optimally for a particular function, context, or domain associated with another entity.
-
D.
instructionMode
Indicates the method or medium through which an instruction, lesson, or teaching activity is delivered.
-
E.
specializationRegion
Indicates that something is specialized, adapted, or specifically applicable to a particular geographic or spatial region.
- 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_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 29, 2026, 8:06 p.m.