Triple
T6843921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hesse |
E157843
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Edersee |
E269254
|
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: Edersee | Statement: [Hesse, contains, Edersee]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Edersee Context triple: [Hesse, contains, Edersee]
-
A.
Edersee
chosen
Edersee is a large artificial reservoir in northern Hesse, Germany, created by the Eder Dam and known for recreation, water sports, and its scenic surroundings.
-
B.
Möhnesee
Möhnesee is a municipality in North Rhine-Westphalia, Germany, known for its large reservoir and scenic recreational area around the Möhne River.
-
C.
Ziegelsee
Ziegelsee is a lake in the city of Schwerin in northern Germany, known for its scenic waterfront and role in the region’s interconnected lake system.
-
D.
Würmsee
Würmsee is the historical name of the Bavarian lake now known as Starnberger See, one of Germany’s largest and most famous lakes near Munich.
-
E.
Salzgittersee
Salzgittersee is a large recreational lake in the city of Salzgitter, Germany, popular for swimming, water sports, and leisure activities.
- 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_69c6882ed4c081909dc465a7cf8838be |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d6b7179481909e3482fef47b2719 |
completed | March 27, 2026, 7:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c72fbf06008190a8c342d3d7dec930 |
completed | March 28, 2026, 1:32 a.m. |
Created at: March 27, 2026, 2:19 p.m.