Triple
T4438490
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Einstein–Szilard refrigerator |
E95710
|
entity |
| Predicate | refrigerantType |
P11564
|
FINISHED |
| Object | non-mechanical absorption system |
—
|
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: non-mechanical absorption system | Statement: [Einstein–Szilard refrigerator, refrigerantType, non-mechanical absorption system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refrigerantType Context triple: [Einstein–Szilard refrigerator, refrigerantType, non-mechanical absorption system]
-
A.
furnaceType
Indicates the specific kind or category of furnace associated with an entity.
-
B.
compressorType
Indicates the specific kind or category of compressor associated with an entity.
-
C.
typeOfGasUsed
Indicates the specific kind of gas that is utilized in relation to an entity or process.
-
D.
coolingMethod
chosen
Indicates the technique or process used to remove heat from something or keep it at a lower temperature.
-
E.
boilerType
Indicates the specific kind or category of boiler associated with an entity, such as its design, fuel source, or operating characteristics.
- 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_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. |
Created at: March 12, 2026, 11:31 p.m.