Triple
T30428468
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sony WH-1000XM3 |
E774095
|
entity |
| Predicate | driverSize |
P17061
|
FINISHED |
| Object | 40 mm |
—
|
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: 40 mm | Statement: [Sony WH-1000XM3, driverSize, 40 mm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: driverSize Context triple: [Sony WH-1000XM3, driverSize, 40 mm]
-
A.
driverDiameter
chosen
Indicates the size of the circular cross-section of a driver component, typically measured as the distance across its widest point.
-
B.
platformSize
Indicates the relative or absolute size or dimensions of a platform in relation to something else.
-
C.
sizeType
Indicates the kind or category of size associated with an entity, such as relative scale, measurement type, or size classification.
-
D.
discSize
Indicates the size or capacity of a disc in the relationship or context being described.
-
E.
weightSize
Indicates a relationship between an entity’s weight and its physical size, typically expressing how one varies or is characterized in terms of the other.
- 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6a916d2e08190bafc01cba73b6469 |
completed | May 3, 2026, 1:47 a.m. |
| PD | Predicate disambiguation | batch_69f6a7548eb48190a69b60a3c6ad53b9 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 29, 2026, 8:06 p.m.