Triple
T14542249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taigei-class submarine |
E341197
|
entity |
| Predicate | hasPowertrain |
P45712
|
FINISHED |
| Object | diesel engines |
—
|
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: diesel engines | Statement: [Taigei-class submarine, hasPowertrain, diesel engines]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPowertrain Context triple: [Taigei-class submarine, hasPowertrain, diesel engines]
-
A.
powertrainComponentOf
Indicates that one entity is a component or subsystem that forms part of the powertrain of another entity.
-
B.
primaryPowertrain
chosen
Indicates the main powertrain system that primarily provides propulsion or drive power for a vehicle or machine.
-
C.
winnerPowertrainType
Indicates the type of powertrain used by the entity that is identified as the winner in a given context or competition.
-
D.
powertrainProduction
Indicates a relationship where an entity is involved in the manufacturing or assembly of a vehicle’s powertrain components.
-
E.
offersPowertrain
Indicates that one entity provides or makes available a specific powertrain to another entity or for a particular product.
- 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_69d822db9c8481908213ceb39585f792 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb1be5a8081909bf727e28a5bba4a |
completed | April 14, 2026, 9:29 p.m. |
| PD | Predicate disambiguation | batch_69de5c546c7081909e27d504ec360c5c |
completed | April 14, 2026, 3:25 p.m. |
Created at: April 10, 2026, 1:22 a.m.