Triple
T33603004
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mazda MX series |
E860770
|
entity |
| Predicate | includesPowertrainType |
P123361
|
FINISHED |
| Object | internal combustion engine |
—
|
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: internal combustion engine | Statement: [Mazda MX series, includesPowertrainType, internal combustion engine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesPowertrainType Context triple: [Mazda MX series, includesPowertrainType, internal combustion engine]
-
A.
winnerPowertrainType
Indicates the type of powertrain used by the entity that is identified as the winner in a given context or competition.
-
B.
powertrainComponentOf
Indicates that one entity is a component or subsystem that forms part of the powertrain of another entity.
-
C.
offersPowertrain
Indicates that one entity provides or makes available a specific powertrain to another entity or for a particular product.
-
D.
powertrainCategory
chosen
Indicates the classification of a vehicle’s powertrain based on how it delivers propulsion (e.g., internal combustion, hybrid, electric).
-
E.
primaryPowertrain
Indicates the main powertrain system that primarily provides propulsion or drive power for a vehicle or machine.
- 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_69f3497f35908190a2e9bbb9b96c7a3f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a032d9200448190a2adcc5ee48bff01 |
completed | May 12, 2026, 1:39 p.m. |
| PD | Predicate disambiguation | batch_6a032c9f41f08190b1c60b0afbbac01a |
completed | May 12, 2026, 1:35 p.m. |
Created at: May 1, 2026, 1:41 a.m.