Triple
T8918191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Celluloid |
E212344
|
entity |
| Predicate | supportsHardwareDecodingViaMpv |
P82506
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [Celluloid, supportsHardwareDecodingViaMpv, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsHardwareDecodingViaMpv Context triple: [Celluloid, supportsHardwareDecodingViaMpv, true]
-
A.
supportsHEVC
Indicates that one entity provides compatibility with or the ability to handle HEVC (High Efficiency Video Coding) for another entity.
-
B.
supportsProResDecode
Indicates that one entity is capable of decoding or otherwise handling ProRes-encoded media for another entity or in a given context.
-
C.
supportsHardwareAcceleration
chosen
Indicates that one entity enables or provides hardware-based acceleration capabilities for another entity’s operations or processes.
-
D.
supportsIntelQuickSyncVideo
Indicates that one entity provides compatibility with or functional support for Intel Quick Sync Video hardware-accelerated video processing.
-
E.
supportsHEVCEncode
Indicates that one entity provides the capability for another entity to perform HEVC (High Efficiency Video Coding) encoding.
- 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_69ca8393b1808190bd4336787ffa2c40 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66120eb08190913ab6c42f26ffb8 |
completed | April 1, 2026, 12:25 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed0ef3c81908cc69eac852ee12a |
completed | March 31, 2026, 11:54 p.m. |
Created at: March 30, 2026, 6:56 p.m.