Triple
T4438478
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Einstein–Szilard refrigerator |
E95710
|
entity |
| Predicate | usesWorkingFluid |
P56023
|
FINISHED |
| Object | butane |
—
|
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: butane | Statement: [Einstein–Szilard refrigerator, usesWorkingFluid, butane]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesWorkingFluid Context triple: [Einstein–Szilard refrigerator, usesWorkingFluid, butane]
-
A.
hasCoolingSource
Indicates that one entity provides or serves as a cooling source for another entity.
-
B.
isCryogenic
Indicates that something operates at, is designed for, or involves extremely low (cryogenic) temperatures.
-
C.
hasThermalWaterUse
Indicates that something makes use of thermal water, typically for purposes such as heating, bathing, energy production, or therapeutic applications.
-
D.
usesThermals
Indicates that one entity relies on rising warm air currents (thermals) as a means to gain lift, move, or maintain altitude.
-
E.
usesPropellantType
Indicates that one entity operates or functions using a specific type of propellant as its fuel or reaction mass.
- 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_69b3453ea2b48190a26f154b3b8fece5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3558c75948190875a5fb10eac0597 |
completed | March 13, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69b34f6078cc8190831b89f404198cc5 |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b3505a87b4819083fbbd58870e520b |
completed | March 12, 2026, 11:46 p.m. |
Created at: March 12, 2026, 11:31 p.m.