Triple
T10778344
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | S2W nuclear reactor |
E254251
|
entity |
| Predicate | powerConversionSystem |
P95415
|
FINISHED |
| Object | steam turbine |
—
|
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: steam turbine | Statement: [S2W nuclear reactor, powerConversionSystem, steam turbine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerConversionSystem Context triple: [S2W nuclear reactor, powerConversionSystem, steam turbine]
-
A.
powerConversionMethod
Indicates the method or process by which one form of power or energy is converted into another.
-
B.
electrificationSystem
Indicates the type of electrical power system used to supply energy (typically to infrastructure or vehicles) for operation.
-
C.
primaryPowertrain
Indicates the main powertrain system that primarily provides propulsion or drive power for a vehicle or machine.
-
D.
usesEnergyConversion
Indicates that an entity performs or involves a process where one form of energy is transformed into another to achieve a function or outcome.
-
E.
transferredPowerTo
Indicates that one entity has passed control, authority, or energy to another entity.
- F. None of above. chosen
Provenance (4 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_69d6aa609f008190a294200aefcb7bd5 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d732c25478819093dedec0c8556777 |
completed | April 9, 2026, 5:01 a.m. |
| PD | Predicate disambiguation | batch_69d6f31455648190b5c24690487b1b54 |
completed | April 9, 2026, 12:30 a.m. |
| PDg | Predicate description generation | batch_69d6fa334b8c819082eaf8537084c323 |
completed | April 9, 2026, 1 a.m. |
Created at: April 8, 2026, 9:16 p.m.