Triple
T20368268
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melnik |
E496973
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Sandanski |
—
|
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: Sandanski | Statement: [Melnik, near, Sandanski]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandanski Context triple: [Melnik, near, Sandanski]
-
A.
Sandanski
chosen
Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
-
B.
Sapareva Banya
Sapareva Banya is a Bulgarian spa town renowned for its hot mineral springs and the hottest geyser in continental Europe.
-
C.
Varna
Varna is a small settlement located within the municipality of Osečina in western Serbia.
-
D.
Varna
Varna is a major Bulgarian city on the Black Sea coast known as an important economic, cultural, and maritime center.
-
E.
Sandanski Municipality
Sandanski Municipality is an administrative region in southwestern Bulgaria centered around the spa and tourist town of Sandanski, known for its mild climate and mineral springs.
- 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_69e0b4a4f9b081908a5a021919c21ccb |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e678734b188190bb2c5863023f9f8c |
completed | April 20, 2026, 7:03 p.m. |
Created at: April 16, 2026, 11:26 a.m.