Triple
T13126984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dolby B |
E311868
|
entity |
| Predicate | compressionCharacteristic |
P108191
|
FINISHED |
| Object | level-dependent high-frequency compression |
—
|
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: level-dependent high-frequency compression | Statement: [Dolby B, compressionCharacteristic, level-dependent high-frequency compression]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: compressionCharacteristic Context triple: [Dolby B, compressionCharacteristic, level-dependent high-frequency compression]
-
A.
compressionType
Indicates the method or format used to compress data or content in the relationship.
-
B.
compressionRatio
Indicates the proportional reduction in size or volume achieved when something is compressed compared to its original size.
-
C.
compressionGoal
Indicates the target level or outcome of data size reduction that a compression process aims to achieve.
-
D.
compressionDomain
Indicates a relationship where one entity serves as the domain or context within which another entity’s compression or compression-related process is defined or applied.
-
E.
compressionScope
Indicates the extent or range within which compression is applied to data or content.
- F. None of above. chosen
Provenance (4 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_69d806a9fe888190b081e2d9ea665d6c |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9819aac388190b59bf43cc6a49d0c |
completed | April 10, 2026, 11:02 p.m. |
| PD | Predicate disambiguation | batch_69d98043a74c81908648e6cd0b4c7f71 |
completed | April 10, 2026, 10:57 p.m. |
| PDg | Predicate description generation | batch_69d98134df64819084a5674f9475dcc2 |
completed | April 10, 2026, 11:01 p.m. |
Created at: April 9, 2026, 9:07 p.m.