Triple
T25550377
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AVX |
E640423
|
entity |
| Predicate | extendsRegister |
P158292
|
FINISHED |
| Object | XMM registers to 256-bit YMM registers |
—
|
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: XMM registers to 256-bit YMM registers | Statement: [AVX, extendsRegister, XMM registers to 256-bit YMM registers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: extendsRegister Context triple: [AVX, extendsRegister, XMM registers to 256-bit YMM registers]
-
A.
relatedRegister
Indicates a relationship where one entity is associated with, linked to, or corresponds to a particular register or record in a system.
-
B.
supportsRegistration
Indicates that an entity provides the capability or functionality to handle or accept registration actions or processes.
-
C.
addsRegisterClass
chosen
Indicates that one entity assigns or associates a specific register class with another entity, typically extending or modifying its register-related behavior.
-
D.
relatedRegistry
Indicates that one registry has an association or linkage to another registry.
-
E.
registerType
Indicates that an entity is classified or recorded under a specific type or category within a registration system.
- 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_69e75dc101a881909fd33b02174e9768 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f8c583e48190a2a1f65d80a2b589 |
completed | May 2, 2026, 1:14 p.m. |
| PD | Predicate disambiguation | batch_69f4a0f7c6008190ae8cee3e71e19b94 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 21, 2026, 3:36 p.m.