Triple
T15795473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | კონსტანტინე გამსახურდია |
E382965
|
entity |
| Predicate | სწავლობდა |
P81253
|
FINISHED |
| Object | ფილოლოგია |
—
|
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: ფილოლოგია | Statement: [კონსტანტინე გამსახურდია, სწავლობდა, ფილოლოგია]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: სწავლობდა Context triple: [კონსტანტინე გამსახურდია, სწავლობდა, ფილოლოგია]
-
A.
studiedUnder
Indicates that one entity received instruction, training, or mentorship from another, typically in an academic or apprenticeship context.
-
B.
alsoStudied
chosen
Indicates that an entity pursued additional studies in another subject, field, or institution besides a primary one.
-
C.
studiesFor
Indicates that one entity engages in studying or academic preparation with the purpose of achieving or supporting another entity (such as a goal, exam, or qualification).
-
D.
stoodAtStudAt
Indicates that one entity was positioned or located at a particular stud (e.g., structural post or support point).
-
E.
isStudiedUsing
Indicates that something serves as the method, tool, or approach by which something else is examined, analyzed, or researched.
- 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_69d86da16e188190b89af699f1ed0bfe |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e0b4dc887081909d682ae153f06d97 |
completed | April 16, 2026, 10:07 a.m. |
| PD | Predicate disambiguation | batch_69e00537bd1c81908d6e832792fd934f |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:48 a.m.