Triple
T12682000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dolby B noise reduction |
E302968
|
entity |
| Predicate | effectOnPlaybackWithDecoding |
P101228
|
FINISHED |
| Object | reduced background hiss |
—
|
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: reduced background hiss | Statement: [Dolby B noise reduction, effectOnPlaybackWithDecoding, reduced background hiss]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: effectOnPlaybackWithDecoding Context triple: [Dolby B noise reduction, effectOnPlaybackWithDecoding, reduced background hiss]
-
A.
hasMediaAdaptation
Indicates that a work has been adapted into another medium, such as film, television, or other forms of media.
-
B.
usesCodec
Indicates that one entity employs or relies on a specific codec to encode, decode, or process data.
-
C.
playbackOnly
Indicates that the relationship or action is limited to playing back existing content without allowing modification, recording, or other interactive operations.
-
D.
playbackMethod
chosen
Indicates the manner or technique by which media content is played back or rendered.
-
E.
playableMode
Indicates that a particular mode, configuration, or state can be actively used or played within a system or application.
- 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_69d7bdee64a08190801c6d470aefd723 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961b32dbc81908101fc5f07e26ed3 |
completed | April 10, 2026, 8:46 p.m. |
| PD | Predicate disambiguation | batch_69d960bb64ec8190bd0400cf0cc8b0a7 |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:21 p.m.