Triple
T17666718
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lungernsee |
E440401
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Lungern |
—
|
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: Lungern | Statement: [Lungernsee, nearbySettlement, Lungern]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lungern Context triple: [Lungernsee, nearbySettlement, Lungern]
-
A.
Lungern
chosen
Lungern is a picturesque Swiss village in the canton of Obwalden, known for its lakeside setting amid alpine mountains and its popularity for outdoor recreation.
-
B.
Langenau
Langenau is a small town in the Alb-Donau district of Baden-Württemberg in southern Germany, known for its historic center and proximity to the Swabian Jura.
-
C.
Lülsfeld
Lülsfeld is a small municipality in the Schweinfurt district of Lower Franconia in northern Bavaria, Germany.
-
D.
Langenberg
Langenberg is a prominent mountain in the Rothaargebirge range of Germany, known as the highest peak in the state of North Rhine-Westphalia.
-
E.
Langenfeld
Langenfeld is a town in western Germany, located in the state of North Rhine-Westphalia between Düsseldorf and Cologne.
- 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46ea9d91c81908414ef38c7fb36a4 |
completed | April 19, 2026, 5:56 a.m. |
Created at: April 10, 2026, 9:57 a.m.