Triple
T11267653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kronstadt Naval Cathedral |
E266728
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Kotlin Island |
E73301
|
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: Kotlin Island | Statement: [Kronstadt Naval Cathedral, locatedOn, Kotlin Island]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kotlin Island Context triple: [Kronstadt Naval Cathedral, locatedOn, Kotlin Island]
-
A.
Kotlin Island
chosen
Kotlin Island is a small island in the Gulf of Finland near St. Petersburg, Russia, historically significant as a naval outpost and namesake of the Kotlin programming language.
-
B.
Mykland
Mykland is a small village in Agder county, Norway, known for its rural setting and surrounding forests and lakes.
-
C.
Kerrera
Kerrera is a small Scottish island in the Inner Hebrides, located near Oban on the country’s west coast.
-
D.
Žitný ostrov
Žitný ostrov is a large river island and fertile lowland region in the Danube River, known as one of Central Europe’s biggest river islands and an important agricultural area of southern Slovakia.
-
E.
Sikkeland
Sikkeland is a Norwegian surname most notably associated with the physicist Torbjørn Sikkeland.
- 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_69d6aac8c2f48190ad0596f1f89f0470 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e94f60d48190bc925c3cb88641a8 |
completed | April 9, 2026, 6 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4ccd52c20819093e03bba2fd359b7 |
completed | April 19, 2026, 12:38 p.m. |
Created at: April 8, 2026, 9:31 p.m.