Triple
T20145262
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adigeni Municipality |
E491285
|
entity |
| Predicate | hasBorderWith |
P224
|
FINISHED |
| Object | Abastumani (settlement) |
—
|
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: Abastumani (settlement) | Statement: [Adigeni Municipality, hasBorderWith, Abastumani (settlement)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Abastumani (settlement) Context triple: [Adigeni Municipality, hasBorderWith, Abastumani (settlement)]
-
A.
Abastumani
chosen
Abastumani is a small resort town in southern Georgia, historically known for its mountain climate and therapeutic sanatoriums.
-
B.
Baksan settlement
Baksan settlement is a small populated area in Russia’s Kabardino-Balkaria region, situated in the North Caucasus near Mount Elbrus.
-
C.
Abasár
Abasár is a village in northern Hungary known for its wine production and location near the Mátra Mountains.
-
D.
Абаза
Абаза — это самоназвание абазинского народа, небольшого кавказского этноса, говорящего на абазинском языке и исторически проживающего на Северном Кавказе.
-
E.
Aghstev
Aghstev is a river in the South Caucasus region that flows through parts of Armenia and Azerbaijan.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6265f8f0819080b29c752a574088 |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e6679d89688190ae88d81002d16d6e |
completed | April 20, 2026, 5:51 p.m. |
Created at: April 11, 2026, 11:33 p.m.