Triple
T36271447
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OM (Orchestra Model) guitar |
E892683
|
entity |
| Predicate | hasLowerBoutWidthComparedTo |
P190203
|
FINISHED |
| Object | dreadnought guitar |
—
|
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: dreadnought guitar | Statement: [OM (Orchestra Model) guitar, hasLowerBoutWidthComparedTo, dreadnought guitar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLowerBoutWidthComparedTo Context triple: [OM (Orchestra Model) guitar, hasLowerBoutWidthComparedTo, dreadnought guitar]
-
A.
hasLowerBarLength
Indicates that one entity’s bar length is shorter than the bar length of another entity.
-
B.
hasLowerPart
Indicates that one entity includes another entity as a component specifically located in its lower part or region.
-
C.
narrowerThan
chosen
Indicates that one entity has a smaller width or breadth than another entity.
-
D.
hasLowerDensityThan
Indicates that one entity has a lower density (mass per unit volume) compared to another entity.
-
E.
hasNarrowestWidth
Indicates that one entity has the smallest width dimension compared to a specified set of entities or alternatives.
- 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_69f76e488f34819083e254dbe288c27a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff5285ed74819097e6e2a9084a079a |
completed | May 9, 2026, 3:28 p.m. |
| PD | Predicate disambiguation | batch_69ff51fbe28881908ac8417dff9db81a |
completed | May 9, 2026, 3:25 p.m. |
Created at: May 3, 2026, 4:09 p.m.