Triple
T20088615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shay locomotive |
E496204
|
entity |
| Predicate | hasCylinderOrientation |
P95322
|
FINISHED |
| Object | vertical cylinders |
—
|
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: vertical cylinders | Statement: [Shay locomotive, hasCylinderOrientation, vertical cylinders]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCylinderOrientation Context triple: [Shay locomotive, hasCylinderOrientation, vertical cylinders]
-
A.
hasFieldOrientation
Indicates that one entity has a specified directional or spatial orientation relative to a field (such as magnetic, electric, or visual field).
-
B.
hasOrientation
Indicates that one entity is positioned or directed in a specific spatial or conceptual alignment relative to a reference frame or another entity.
-
C.
cylinderPosition
chosen
Indicates the spatial location or placement of a cylinder relative to a defined reference frame or environment.
-
D.
coneOrientation
Indicates the directional alignment or pointing direction of a cone relative to a reference frame or object.
-
E.
cylindersBankAngle
Indicates the angle at which the cylinders in an engine are arranged or inclined relative to the engine’s central bank or reference plane.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655d65a88190a510132f36341b6c |
completed | April 20, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:17 p.m.