Triple
T35811899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | გარდაბანი |
E1035252
|
entity |
| Predicate | ენერგეტიკული ობიექტების ტიპი |
P125049
|
FINISHED |
| Object | თბოელექტროსადგური |
—
|
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: თბოელექტროსადგური | Statement: [გარდაბანი, ენერგეტიკული ობიექტების ტიპი, თბოელექტროსადგური]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ენერგეტიკული ობიექტების ტიპი Context triple: [გარდაბანი, ენერგეტიკული ობიექტების ტიპი, თბოელექტროსადგური]
-
A.
energyType
Indicates the kind or category of energy associated with an entity or process.
-
B.
energyBaseType
chosen
Indicates the fundamental category or source type of energy associated with an entity or process.
-
C.
energyBase
Indicates that one entity serves as the fundamental source or basis of energy for another entity or process.
-
D.
typicalObjectType
Indicates that something is a common or characteristic type of object typically associated with or involved in another entity or situation.
-
E.
derivesPowerFrom
Indicates that one entity obtains or is granted its power, authority, or energy as a result of another entity.
- 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_69f76e1762408190b885a8456862e372 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7bbf906d8819099020e548dd56bc9 |
completed | May 3, 2026, 9:19 p.m. |
| PD | Predicate disambiguation | batch_69f7b9a2dcf88190a7c9e109e41267be |
completed | May 3, 2026, 9:09 p.m. |
Created at: May 3, 2026, 4:06 p.m.