Triple
T38324563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | აკაკი წერეთლის მუზეუმი |
E1036747
|
entity |
| Predicate | მფარველი პიროვნება |
P175048
|
FINISHED |
| Object | აკაკი წერეთელი |
—
|
NE NERFINISHED |
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: აკაკი წერეთელი | Statement: [აკაკი წერეთლის მუზეუმი, მფარველი პიროვნება, აკაკი წერეთელი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: მფარველი პიროვნება Context triple: [აკაკი წერეთლის მუზეუმი, მფარველი პიროვნება, აკაკი წერეთელი]
-
A.
מאפיין מסורתי
Indicates a traditional characteristic or attribute that is typically associated with something based on long-standing customs or heritage.
-
B.
भूमिका
chosen
Indicates a relationship where an entity serves, functions, or acts in a particular capacity or role with respect to another entity or context.
-
C.
مجال الشهرة
Indicates the domain or field in which an entity is renowned or widely recognized.
-
D.
საფარი
Indicates that one entity serves as a covering, coating, or protective layer over another entity.
-
E.
التأثير
Indicates a relationship where one entity produces a change or has an influence on another entity or its state.
- 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_69f76e1c16fc8190bde982289dd5106b |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fccbd826708190b5fab12c4236299a |
completed | May 7, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69fcc58838e08190b8fa54aa5c165f2d |
completed | May 7, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:30 p.m.