Triple
T23113534
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Schweriner See |
E576385
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Kaninchenwerder |
E908608
|
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: Kaninchenwerder | Statement: [Schweriner See, hasIsland, Kaninchenwerder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kaninchenwerder Context triple: [Schweriner See, hasIsland, Kaninchenwerder]
-
A.
Kaninchenwerder
chosen
Kaninchenwerder is a small, uninhabited island and nature reserve in Lake Schwerin in northern Germany, known for its rich birdlife and protected natural landscapes.
-
B.
Ziegelwerder
Ziegelwerder is an island located within Lake Schwerin in northern Germany.
-
C.
Schwanenwerder
Schwanenwerder is a small, affluent island neighborhood in southwestern Berlin, known for its exclusive villas and scenic location in the River Havel.
-
D.
Baumwerder
Baumwerder is a small island located in Tegeler See, a lake in the Berlin district of Reinickendorf, Germany.
-
E.
Brühlwiese
Brühlwiese is a festival meadow in Bad Dürkheim, Germany, best known as the traditional site of the town’s famous Wurstmarkt wine and sausage fair.
- 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e1121c08190a1d29fe594071c46 |
completed | April 29, 2026, 4:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c23ec62f08190a4dda0d537a7b024 |
completed | May 19, 2026, 8:48 a.m. |
Created at: April 17, 2026, 3:59 p.m.