Triple
T32076989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AMD Radeon RX Vega series |
E819181
|
entity |
| Predicate | multiGPUSolution |
P173514
|
FINISHED |
| Object | AMD CrossFire |
—
|
NE NERFINISHED |
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: AMD CrossFire | Statement: [AMD Radeon RX Vega series, multiGPUSolution, AMD CrossFire]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: multiGPUSolution Context triple: [AMD Radeon RX Vega series, multiGPUSolution, AMD CrossFire]
-
A.
usesNumberOfGPUs
Indicates that an entity operates with, depends on, or is configured to utilize a specified number of GPUs.
-
B.
integratesGPU
Indicates that one entity incorporates or embeds a GPU as a functional component within its design or system.
-
C.
maxNVLinkGPUs
Indicates the maximum number of GPUs that can be interconnected via NVLink in a given configuration or system.
-
D.
supportsParallelProgrammingModel
Indicates that one entity provides facilities or mechanisms enabling the use of a parallel programming model with another entity.
-
E.
supportsMixedPrecision
Indicates that one entity is capable of correctly handling or executing operations that use a combination of different numeric precisions (e.g., mixed-precision computation) in relation to another entity or process.
- F. None of above. chosen
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_69f348ff8ef88190931c08ba530a36bc |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b56ed31481908c3e5d749e46bad9 |
completed | May 3, 2026, 2:39 a.m. |
| PD | Predicate disambiguation | batch_69f6b3a7bdb481908d16a32f49e38c2c |
completed | May 3, 2026, 2:32 a.m. |
| PDg | Predicate description generation | batch_69f6b49339048190b617a6749f648825 |
completed | May 3, 2026, 2:36 a.m. |
Created at: May 1, 2026, 12:23 a.m.