Triple
T25540246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cherry Trail |
E640156
|
entity |
| Predicate | supportsVideoDecoding |
P102952
|
FINISHED |
| Object | H.264 hardware decode |
—
|
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: H.264 hardware decode | Statement: [Cherry Trail, supportsVideoDecoding, H.264 hardware decode]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsVideoDecoding Context triple: [Cherry Trail, supportsVideoDecoding, H.264 hardware decode]
-
A.
supportsVideoPlayback
Indicates that an entity is capable of playing or rendering video content.
-
B.
supportsH264
chosen
Indicates that one entity provides compatibility with, or the ability to encode/decode or process, H.264 video for another entity.
-
C.
supportsHEVC
Indicates that one entity provides compatibility with or the ability to handle HEVC (High Efficiency Video Coding) for another entity.
-
D.
supportsProResDecode
Indicates that one entity is capable of decoding or otherwise handling ProRes-encoded media for another entity or in a given context.
-
E.
supportsIntelQuickSyncVideo
Indicates that one entity provides compatibility with or functional support for Intel Quick Sync Video hardware-accelerated video processing.
- 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_69e75dbfff7081909b0aa779d48321d2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
Created at: April 21, 2026, 3:25 p.m.