Triple
T30350564
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sony WH-XB910N |
E771977
|
entity |
| Predicate | noiseControlType |
P107588
|
FINISHED |
| Object | active noise cancellation |
—
|
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: active noise cancellation | Statement: [Sony WH-XB910N, noiseControlType, active noise cancellation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: noiseControlType Context triple: [Sony WH-XB910N, noiseControlType, active noise cancellation]
-
A.
noisePolicy
Indicates the rules or constraints governing acceptable noise levels or noise-related behavior in a given context.
-
B.
noiseLevel
Indicates the intensity or amount of sound present in a given environment or from a specific source.
-
C.
noiseReductionType
chosen
Indicates the specific method or technique used to reduce or minimize noise in a given context.
-
D.
noiseCompliance
Indicates that an entity adheres to specified rules or standards governing acceptable noise levels or sound emissions.
-
E.
targetsNoiseType
Indicates that an entity is directed at, designed for, or specifically affects a particular type or category of noise.
- 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_69f2248b9a208190bc3e6804acd5afd6 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6820b4b8c81908f5bbae956565ec0 |
completed | May 2, 2026, 11 p.m. |
| PD | Predicate disambiguation | batch_69f67e40af9881908de3a4aa15f70a83 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 29, 2026, 7:56 p.m.