Triple
T30698614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sony α7 IV |
E781547
|
entity |
| Predicate | videoSubsampling |
P99569
|
FINISHED |
| Object | 4:2:2 internal |
—
|
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: 4:2:2 internal | Statement: [Sony α7 IV, videoSubsampling, 4:2:2 internal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: videoSubsampling Context triple: [Sony α7 IV, videoSubsampling, 4:2:2 internal]
-
A.
videoOversampling
Indicates that a video has been sampled or processed at a higher temporal or spatial resolution than the original source, typically to improve quality or enable more detailed analysis.
-
B.
chromaSubsamplingOptions
chosen
Indicates how color information is reduced or sampled relative to luminance in an image or video signal.
-
C.
commonlyUsedColorSubsampling
Indicates that a particular color subsampling scheme is frequently or typically used in practice.
-
D.
videoEncoding
Indicates that one entity is used to encode, compress, or transform video data into a particular digital format or representation for another entity.
-
E.
videoStandard
Indicates the video format or broadcasting standard that applies to a given video or recording.
- 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_69f224ab24e08190991d6edb6df58e8b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6b21e7e088190832a3db585daea1c |
completed | May 3, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: April 29, 2026, 8:34 p.m.