Triple
T29949097
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ATI Flipper |
E760720
|
entity |
| Predicate | alphaChannelDepth |
P164965
|
FINISHED |
| Object | 8-bit alpha |
—
|
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: 8-bit alpha | Statement: [ATI Flipper, alphaChannelDepth, 8-bit alpha]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alphaChannelDepth Context triple: [ATI Flipper, alphaChannelDepth, 8-bit alpha]
-
A.
supportsAlphaBitDepth
chosen
Indicates that one entity is capable of handling or providing image or video data with an alpha (transparency) channel at a specified bit depth.
-
B.
colorDepth
Indicates the bit-depth used to represent the color information of an image or display, defining how many distinct colors can be shown.
-
C.
inputColorChannels
Indicates the specific color channels that are provided as input to a process, function, or model.
-
D.
hasChannelDepth
Indicates that one entity specifies or records the depth measurement of a channel associated with another entity.
-
E.
imageChannels
Indicates the number and types of color or data channels present in an image (e.g., RGB, RGBA, grayscale).
- 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_69f2246562b881909d57622f4086d43d |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6780dd5d08190b1ef4e49405a5419 |
completed | May 2, 2026, 10:17 p.m. |
| PD | Predicate disambiguation | batch_69f66ec8298c8190b41fe9d182c05676 |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 29, 2026, 6:25 p.m.