Triple
T23014166
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danubian Bulgaria |
E572985
|
entity |
| Predicate | laterCapital |
P204
|
FINISHED |
| Object | Ohrid |
—
|
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: Ohrid | Statement: [Danubian Bulgaria, laterCapital, Ohrid]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ohrid Context triple: [Danubian Bulgaria, laterCapital, Ohrid]
-
A.
Ohrid
chosen
Ohrid is a historic lakeside city in North Macedonia renowned as an early Slavic Christian and cultural center, famed for its medieval churches and monasteries.
-
B.
Skadar
Skadar is a small settlement located within the municipality of Osečina in western Serbia.
-
C.
Imotski
Imotski is a small historic town in inland Dalmatia, Croatia, known for its karst landscape and the nearby Blue and Red Lakes.
-
D.
Berane
Berane is a town and municipality in northeastern Montenegro, situated in the Lim River valley and serving as a regional economic and cultural center.
-
E.
Dojran
Dojran is a town in southeastern North Macedonia near the Greek border, known for its proximity to Lake Dojran and its historical significance dating back to ancient and Ottoman times.
- 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_69e245b764cc8190a51be76f1d9611e1 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f183e3c0e08190a7ac747b056ec3ca |
completed | April 29, 2026, 4:06 a.m. |
Created at: April 17, 2026, 3:51 p.m.