Triple
T15127157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Karelian |
E361319
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Olonets Karelian |
E359876
|
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: Olonets Karelian | Statement: [South Karelian, closelyRelatedTo, Olonets Karelian]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Olonets Karelian Context triple: [South Karelian, closelyRelatedTo, Olonets Karelian]
-
A.
Olonets Karelian
chosen
Olonets Karelian is a major dialect of the Karelian language spoken primarily in the Republic of Karelia in northwestern Russia.
-
B.
Ladoga Karelia
Ladoga Karelia is a historical region in southeastern Finland, bordering Lake Ladoga, that was ceded to the Soviet Union after the Winter War.
-
C.
Onega
Onega is a small town in Arkhangelsk Oblast, northwestern Russia, situated near the mouth of the Onega River on the White Sea coast.
-
D.
Onega River
The Onega River is a major river in northwestern Russia that flows through the Karelia region before emptying into the White Sea.
-
E.
White Sea Karelia
White Sea Karelia is a coastal region of Karelia in northwestern Russia, characterized by its location along the White Sea and its sparsely populated, forested and maritime landscapes.
- 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_69d85a06450081909c5a14ea9851a15e |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e005a1b9288190954f2d92549805e5 |
completed | April 15, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69feb7f865c08190ab8fd15c14d0c06c |
completed | May 9, 2026, 4:28 a.m. |
Created at: April 10, 2026, 3:06 a.m.