Triple
T13989896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gnome Monosoupape rotary engine |
E336540
|
entity |
| Predicate | crankshaft |
P65156
|
FINISHED |
| Object | fixed crankshaft with rotating cylinders and crankcase |
—
|
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: fixed crankshaft with rotating cylinders and crankcase | Statement: [Gnome Monosoupape rotary engine, crankshaft, fixed crankshaft with rotating cylinders and crankcase]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crankshaft Context triple: [Gnome Monosoupape rotary engine, crankshaft, fixed crankshaft with rotating cylinders and crankcase]
-
A.
crankshaftType
chosen
Indicates the specific design or configuration of a crankshaft that an entity uses or is associated with.
-
B.
camshaftType
Indicates the specific design or configuration of camshaft associated with an engine or mechanical system.
-
C.
camshaftConfiguration
Indicates how the camshafts are arranged or configured within an engine’s valve train system.
-
D.
shaftCount
Indicates the number of shafts associated with or contained in an object or system.
-
E.
propulsionShafts
Indicates a relationship where shafts are used to transmit mechanical power for propulsion between components of a system.
- 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_69d81c639e808190a0e4b4f3d31c6a59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2eb22e388190904fc87765176c91 |
completed | April 14, 2026, 12:10 p.m. |
| PD | Predicate disambiguation | batch_69dd465dfbc4819090d8c61fd572d35f |
completed | April 13, 2026, 7:39 p.m. |
Created at: April 9, 2026, 10:18 p.m.