Triple
T33078318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paks Nuclear Power Plant |
E846430
|
entity |
| Predicate | PaksIIReactorType |
P171735
|
FINISHED |
| Object | VVER-1200 |
—
|
NE NERFINISHED |
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: VVER-1200 | Statement: [Paks Nuclear Power Plant, PaksIIReactorType, VVER-1200]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: PaksIIReactorType Context triple: [Paks Nuclear Power Plant, PaksIIReactorType, VVER-1200]
-
A.
hasNuclearReactorType
chosen
Indicates that an entity possesses or is equipped with a specific type or classification of nuclear reactor.
-
B.
electricalCapacityPerReactor_MWe
Indicates the electrical power output capacity, measured in megawatts electric (MWe), that is provided by each individual reactor.
-
C.
nuclearPowerStationUnit
Indicates a relationship where an individual unit (such as a reactor or generating block) is part of or belongs to a specific nuclear power station.
-
D.
thermalNeutronReactor
Indicates that the subject is a nuclear reactor that operates using thermal (low-energy) neutrons to sustain its fission chain reaction.
-
E.
propulsionReactorType
Indicates the type or kind of reactor used as the primary source of propulsion.
- 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_69f34954d46c8190a04a159cc5f99efd |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d6a6b04c8190bee4cf9c00665ef7 |
completed | May 3, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69f6d27120988190aacec621cf2bf0e8 |
completed | May 3, 2026, 4:43 a.m. |
Created at: May 1, 2026, 1:25 a.m.