Triple
T11993159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Newcomen atmospheric engine |
E285462
|
entity |
| Predicate | workingFluid |
P56023
|
FINISHED |
| Object | water steam |
—
|
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: water steam | Statement: [Newcomen atmospheric engine, workingFluid, water steam]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workingFluid Context triple: [Newcomen atmospheric engine, workingFluid, water steam]
-
A.
usesWorkingFluid
chosen
Indicates that one entity operates or functions by employing another entity as its working fluid.
-
B.
heatTransferMedium
Indicates that one entity serves as the medium or carrier through which heat is transferred from one place or object to another.
-
C.
hasFluid
Indicates that one entity contains, holds, or is associated with a particular fluid.
-
D.
coolant
Indicates that one entity functions as a coolant for another, serving to absorb and remove heat from it.
-
E.
hasCoolingFlow
Indicates that an entity is equipped with or utilizes a system or mechanism to remove heat or maintain a lower temperature through the flow of a cooling medium.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903b11ac481909866b611380792e7 |
completed | April 10, 2026, 2:05 p.m. |
| PD | Predicate disambiguation | batch_69d902abca70819098291aa51b593708 |
completed | April 10, 2026, 2:01 p.m. |
Created at: April 8, 2026, 9:46 p.m.