Triple
T35895679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | აღმოსავლეთი საქართველო |
E1038215
|
entity |
| Predicate | მნიშვნელოვანი ქალაქი |
P22141
|
FINISHED |
| Object | თბილისი |
—
|
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: თბილისი | Statement: [აღმოსავლეთი საქართველო, მნიშვნელოვანი ქალაქი, თბილისი]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: მნიშვნელოვანი ქალაქი Context triple: [აღმოსავლეთი საქართველო, მნიშვნელოვანი ქალაქი, თბილისი]
-
A.
გამდინარე_ქალაქი
Indicates that a city serves as the outlet or discharge point (e.g., where a river flows out).
-
B.
wasImportantCityOf
chosen
Indicates that a city held significant importance or prominence within a specified larger political or geographic entity during a given time period.
-
C.
notableHumanSettlement
Indicates that a location is recognized as a significant or noteworthy human settlement, such as a city, town, or village.
-
D.
עיר מוצא
Indicates the city from which an entity originates or comes.
-
E.
capitalOrMajorCenter
Indicates that a location serves as a capital city or a primary major center (political, economic, or cultural hub) for a larger region or 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_69f76e2190f88190beb2eed798a4ef01 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa3da83c81908f55bff672e91892 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d435288190b30b1991fb003121 |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.