Triple
T482502
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | N Reactor |
E9800
|
entity |
| Predicate | powerOutputThermal |
P10373
|
FINISHED |
| Object | approximately 4000 MWt |
—
|
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: approximately 4000 MWt | Statement: [N Reactor, powerOutputThermal, approximately 4000 MWt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: powerOutputThermal Context triple: [N Reactor, powerOutputThermal, approximately 4000 MWt]
-
A.
designPowerOutput
chosen
Indicates the intended or specified power output level that something is designed to produce under defined conditions.
-
B.
operatingTemperature
Indicates the range or specific value of temperature within which an entity is designed or allowed to function properly.
-
C.
enginePower
Indicates the power output produced by an engine, typically quantifying its capability to perform work or generate mechanical energy.
-
D.
powerDirection
Indicates the direction in which power, influence, or control flows from one entity to another.
-
E.
maximumPowerDeliveredToPD
Indicates the highest level of electrical power that can be supplied to the power-drawing device (PD) in this relationship.
- 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_69a2e802e2908190ab17c9479e0b6412 |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2f05a7f6c819082b4a5a3e69468a6 |
completed | Feb. 28, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_69a2edf321288190b5d560f75782c2cb |
completed | Feb. 28, 2026, 1:30 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.