Triple
T4921534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bulgarian Navy (World War II) |
E110476
|
entity |
| Predicate | usedPort |
P23954
|
FINISHED |
| Object | Sozopol |
E477835
|
NE FINISHED |
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: Sozopol | Statement: [Bulgarian Navy (World War II), usedPort, Sozopol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sozopol Context triple: [Bulgarian Navy (World War II), usedPort, Sozopol]
-
A.
Sozopol
chosen
Sozopol is an ancient coastal town and popular seaside resort on Bulgaria’s Black Sea coast, known for its historic architecture and maritime heritage.
-
B.
Balchik
Balchik is a coastal town and resort on the Black Sea in northeastern Bulgaria, known for its picturesque cliffs, botanical garden, and the former Romanian Queen Marie’s palace.
-
C.
Pavlograd
Pavlograd is a city in eastern Ukraine known historically as a regional industrial and transport center in the Dnipropetrovsk area.
-
D.
Arachova
Arachova is a picturesque mountain town in central Greece, known for its traditional stone architecture, ski resort, and proximity to the ancient site of Delphi.
-
E.
Sandanski
Sandanski is a town in southwestern Bulgaria known as a spa and climatic resort in the Struma River valley near the Greek border.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69bd4413f9908190afcff44d7929cc4c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ffc2ab08190992db2400562bcee |
completed | March 20, 2026, 4:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be77a41ca08190a8fbfa405b15d68c |
completed | March 21, 2026, 10:49 a.m. |
Created at: March 20, 2026, 1:30 p.m.