Triple
T38309306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AMD CDNA 2 |
E1033640
|
entity |
| Predicate | supportsSoftwareStack |
P35880
|
FINISHED |
| Object | ROCm |
E956196
|
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: ROCm | Statement: [AMD CDNA 2, supportsSoftwareStack, ROCm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsSoftwareStack Context triple: [AMD CDNA 2, supportsSoftwareStack, ROCm]
-
A.
supportsSoftwareEcosystem
chosen
Indicates that one entity provides resources, compatibility, or infrastructure that enables another entity’s software ecosystem to function, grow, or be maintained.
-
B.
supportedIn
Indicates that one entity is valid, applicable, or functionally enabled within the context, environment, platform, or scope defined by another entity.
-
C.
supportsFeature
Indicates that one entity provides, enables, or is compatible with a particular feature or capability of another.
-
D.
supportedAs
Indicates that one entity is accepted, recognized, or treated as being in the role, type, or representation of another entity.
-
E.
supportsAt
Indicates that one entity provides assistance, endorsement, or backing to another entity in a specific context, location, or point in time.
- F. None of above.
Provenance (4 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_69f76e132c408190969b3d35c04b87ae |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c903be48190a2fafa53d7d50d42 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41b290c3588190a80697fc442b0f18 |
completed | June 28, 2026, 11:47 p.m. |
| PD | Predicate disambiguation | batch_6a037a1c850c819088795a7ae59bdeb8 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:30 p.m.