Triple
T15795590
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ეკატერინე გაბაშვილი |
E382968
|
entity |
| Predicate | ცნობილია როგორც |
P84972
|
FINISHED |
| Object | ერთ-ერთი პირველი ფემინისტი საქართველოში |
—
|
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: ერთ-ერთი პირველი ფემინისტი საქართველოში | Statement: [ეკატერინე გაბაშვილი, ცნობილია როგორც, ერთ-ერთი პირველი ფემინისტი საქართველოში]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ცნობილია როგორც Context triple: [ეკატერინე გაბაშვილი, ცნობილია როგორც, ერთ-ერთი პირველი ფემინისტი საქართველოში]
-
A.
известенКак
Indicates that one entity is known or recognized by a particular name, title, or role.
-
B.
известноКак
chosen
Indicates that one entity is known or referred to by another name, designation, or alias.
-
C.
известенС
Indicates that one entity is known or recognized by another entity.
-
D.
isWidelyKnown
Indicates that something is generally recognized or familiar to a large number of people.
-
E.
knownAsOneOf
Indicates that an entity is recognized or referred to as one member of a specified set of alternative names, labels, or identities.
- 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.