Triple
T38324567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | აკაკი წერეთლის მუზეუმი |
E1036747
|
entity |
| Predicate | თემატიკა |
P186092
|
FINISHED |
| Object | ლიტერატურული მუზეუმი |
—
|
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: ლიტერატურული მუზეუმი | Statement: [აკაკი წერეთლის მუზეუმი, თემატიკა, ლიტერატურული მუზეუმი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: თემატიკა Context triple: [აკაკი წერეთლის მუზეუმი, თემატიკა, ლიტერატურული მუზეუმი]
-
A.
associatedMatha
Indicates a relationship where one entity is linked or affiliated with a particular matha (monastic or religious institution).
-
B.
موضوعه
chosen
Indicates that something is the subject or topic that an action, statement, or discussion is about.
-
C.
mathematicalSubjectClassification
Indicates that one entity classifies the mathematical subject area or field to which another entity (such as a work, concept, or topic) belongs.
-
D.
mathematicalSchool
Indicates a relationship where an entity is associated with, belongs to, or is characterized by a particular school or tradition within mathematics.
-
E.
treatsMathematicsAs
Indicates how an entity regards, approaches, or conceptualizes mathematics (e.g., as a tool, language, art, or science).
- 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.