Triple
T1890094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burgas |
E41854
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Lake Burgas |
E210200
|
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: Lake Burgas | Statement: [Burgas, locatedNear, Lake Burgas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lake Burgas Context triple: [Burgas, locatedNear, Lake Burgas]
-
A.
Bay of Varna
The Bay of Varna is a Black Sea coastal inlet in northeastern Bulgaria, forming the maritime setting and harbor area for the city of Varna.
-
B.
Burgas Bay
chosen
Burgas Bay is a large bay on Bulgaria’s Black Sea coast, known for its major port city of Burgas and its role as an important regional maritime and industrial hub.
-
C.
Lake Dojran
Lake Dojran is a shallow, biodiversity-rich lake on the border between North Macedonia and Greece, known for its traditional fishing methods and important wetland habitats.
-
D.
Blagoevgradska Bistritsa
Blagoevgradska Bistritsa is a river in southwestern Bulgaria that flows through the city of Blagoevgrad before joining the Struma River.
-
E.
Lake Velence
Lake Velence is one of Hungary’s largest natural lakes, known as a popular resort and recreation area in the Transdanubian region.
- 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_69a8864b6de0819098d089f6a1b910a7 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb14475448190b291ada3454bf98b |
completed | March 7, 2026, 5:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69adeae81e4c8190bf480215a8a33630 |
completed | March 8, 2026, 9:32 p.m. |
Created at: March 4, 2026, 7:34 p.m.