Triple
T31336866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | L-twin |
E799197
|
entity |
| Predicate | hasRearCylinderOrientation |
P181621
|
FINISHED |
| Object | nearly vertical rear cylinder |
—
|
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: nearly vertical rear cylinder | Statement: [L-twin, hasRearCylinderOrientation, nearly vertical rear cylinder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRearCylinderOrientation Context triple: [L-twin, hasRearCylinderOrientation, nearly vertical rear cylinder]
-
A.
cylinderOrientation
chosen
Indicates the spatial orientation or rotational alignment of a cylinder relative to a reference frame or other object.
-
B.
isOnRearPlate
Indicates that one entity is positioned on or attached to the rear plate of another entity.
-
C.
hasRearUnitType
Indicates that an entity’s rear section or back part is of a specified type.
-
D.
shaftOrientation
Indicates the directional alignment or angle at which a shaft is positioned or oriented relative to a reference frame or object.
-
E.
ringOrientation
Indicates the spatial alignment or facing direction of a ring relative to a reference frame or object.
- 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_69f224e3f6ac8190a13488516abca7c9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_6a0141fceb908190863778741bd4487d |
completed | May 11, 2026, 2:42 a.m. |
| PD | Predicate disambiguation | batch_6a0141a9628c819090c0b24ce052a2fb |
completed | May 11, 2026, 2:40 a.m. |
Created at: April 29, 2026, 9:16 p.m.