Triple
T19530859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ondol |
E488647
|
entity |
| Predicate | energyCharacteristic |
P128001
|
FINISHED |
| Object | high thermal mass |
—
|
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: high thermal mass | Statement: [Ondol, energyCharacteristic, high thermal mass]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: energyCharacteristic Context triple: [Ondol, energyCharacteristic, high thermal mass]
-
A.
energyEfficiencyFeature
Indicates that an entity has a design, technology, or characteristic specifically intended to reduce energy consumption or improve energy performance.
-
B.
dataCharacteristic
Indicates that one entity specifies a property, attribute, or feature that characterizes a given piece of data.
-
C.
entityCharacteristic
chosen
Indicates that an entity possesses, exhibits, or is defined by a particular characteristic or attribute.
-
D.
valueCharacteristic
Indicates that one entity serves as a value or specific quantitative/qualitative measure that characterizes or describes another entity.
-
E.
energyUse
Indicates the amount or rate at which an entity consumes energy to perform its functions or activities.
- 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_69d8e8db5b6c8190984b61f91981f575 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6363ec6cc8190b9e9ac0196b288f9 |
completed | April 20, 2026, 2:20 p.m. |
| PD | Predicate disambiguation | batch_69e514c9c00481909b76bda67957e58b |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:41 p.m.