Triple
T22904115
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PM-3A nuclear reactor |
E568399
|
entity |
| Predicate | heatSupply |
P38384
|
FINISHED |
| Object | space heating for McMurdo Station buildings |
—
|
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: space heating for McMurdo Station buildings | Statement: [PM-3A nuclear reactor, heatSupply, space heating for McMurdo Station buildings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: heatSupply Context triple: [PM-3A nuclear reactor, heatSupply, space heating for McMurdo Station buildings]
-
A.
heatSource
chosen
Indicates that one entity serves as a source of heat or heating for another entity.
-
B.
commonHeatingFuel
Indicates that two entities share the same type of heating fuel used for heating purposes.
-
C.
thermalPower
Indicates the amount of heat energy per unit time that a system, device, or process generates, transfers, or consumes.
-
D.
primaryHeatingFuel
Indicates the type of fuel or energy source that is mainly used for heating a building or space.
-
E.
heatFlow
Indicates the transfer of thermal energy from one entity or region to another due to a temperature difference.
- 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_69e2458cd9e48190943ad2e34485d939 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1801895f48190bb8d49a41feac7ef |
completed | April 29, 2026, 3:50 a.m. |
| PD | Predicate disambiguation | batch_69ef3b6b2e2481908258156937b5a745 |
completed | April 27, 2026, 10:33 a.m. |
Created at: April 17, 2026, 3:41 p.m.