Triple
T24524253
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Singer Model 15 |
E606621
|
entity |
| Predicate | stitchAdjustment |
P31649
|
FINISHED |
| Object | adjustable stitch length |
—
|
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: adjustable stitch length | Statement: [Singer Model 15, stitchAdjustment, adjustable stitch length]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: stitchAdjustment Context triple: [Singer Model 15, stitchAdjustment, adjustable stitch length]
-
A.
stitchTypeUsed
Indicates that a particular type of stitch is employed in performing or constructing the referenced action or object.
-
B.
stitchStructure
Indicates a relationship where one entity joins or binds parts of another entity together in a continuous, stitch-like structural manner.
-
C.
adjustsFor
Indicates that one entity modifies, compensates, or accounts for the effects of another entity to achieve a corrected or normalized result.
-
D.
adjustmentType
chosen
Indicates the specific kind or category of modification applied to an existing value, state, or configuration within the relationship.
-
E.
buttstockAdjustability
Indicates whether and how the buttstock of a firearm can be adjusted (e.g., for length, height, or angle) relative to the rest of the weapon.
- 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_69e2c4c85778819085f5da9af3569ad5 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:25 a.m.