Triple
T2928275
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ThunderDome |
E78896
|
entity |
| Predicate | indoorClimateControl |
P23545
|
FINISHED |
| Object | air conditioned |
—
|
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: air conditioned | Statement: [ThunderDome, indoorClimateControl, air conditioned]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: indoorClimateControl Context triple: [ThunderDome, indoorClimateControl, air conditioned]
-
A.
thermalControl
chosen
Indicates a relationship where one entity regulates, adjusts, or maintains the temperature or thermal conditions of another entity or environment.
-
B.
settingClimate
Indicates that an entity adjusts or defines the climate or environmental conditions for another entity or context.
-
C.
temperatureControlMethod
Indicates the method or mechanism used to regulate or maintain a desired temperature.
-
D.
ventilationFeature
Indicates that one entity has a structural or functional role related to providing, enabling, or affecting ventilation for another entity.
-
E.
climateControlledCabins
Indicates that the subject provides or features cabins whose internal environment (such as temperature and humidity) is actively regulated for comfort or preservation.
- 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_69ad8b0d40b481908bc2a5fa2e73c3fb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97ff0ddc8190acba9863bbe4f54b |
completed | March 8, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9606e8348190bb19df33a2709674 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:55 p.m.