Triple
T19364973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Bulgaria |
E484377
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Chepelare |
—
|
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: Chepelare | Statement: [Southern Bulgaria, hasMajorCity, Chepelare]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chepelare Context triple: [Southern Bulgaria, hasMajorCity, Chepelare]
-
A.
Chepelare
chosen
Chepelare is a small Bulgarian mountain town and ski resort located in the Rhodope Mountains, known for its winter sports facilities and scenic surroundings.
-
B.
Tighina
Tighina is a historic city in present-day Moldova, also known as Bender, which has long held strategic importance on the Dniester River.
-
C.
Zimnicea
Zimnicea is a town in southern Romania situated on the Danube River near the border with Bulgaria.
-
D.
Eforie
Eforie is a Romanian Black Sea resort town known for its beaches and therapeutic mud treatments.
-
E.
Sinaia
Sinaia is a Romanian mountain resort town in the Carpathians, famed for Peleș Castle and its historic role as a royal summer residence.
- 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_69d8e8d305088190ad13571532aa454c |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e619aa9ff48190b1ede47fb88a682e |
completed | April 20, 2026, 12:18 p.m. |
Created at: April 10, 2026, 1:35 p.m.