Triple
T1866085
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | X-10 graphite reactor |
E34923
|
entity |
| Predicate | initialThermalPower |
P18503
|
FINISHED |
| Object | 1000 kW |
—
|
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: 1000 kW | Statement: [X-10 graphite reactor, initialThermalPower, 1000 kW]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: initialThermalPower Context triple: [X-10 graphite reactor, initialThermalPower, 1000 kW]
-
A.
thermalPower
chosen
Indicates the amount of heat energy per unit time that a system, device, or process generates, transfers, or consumes.
-
B.
powerplant
Indicates that an entity functions as a facility or installation where energy sources are converted into usable power, typically electricity.
-
C.
powerplantType
Indicates the specific kind or category of power plant associated with an entity, based on how it generates energy.
-
D.
intendedPower
Indicates the level or amount of power that an entity is designed, planned, or expected to produce, use, or deliver under intended operating conditions.
-
E.
maximumPowerDuringOperation
Indicates the highest level of power that occurs while the system or component is operating.
- 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_69a88600b2f88190bc09303e68ab517e |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69abb16c09e48190a345c95eab59fd87 |
completed | March 7, 2026, 5:02 a.m. |
| PD | Predicate disambiguation | batch_69abafe02c3c819093a4744b476106ca |
completed | March 7, 2026, 4:56 a.m. |
Created at: March 4, 2026, 7:34 p.m.