Triple
T22543966
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eiderstedt Peninsula |
E557367
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Tönning |
—
|
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: Tönning | Statement: [Eiderstedt Peninsula, contains, Tönning]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tönning Context triple: [Eiderstedt Peninsula, contains, Tönning]
-
A.
Tönning
chosen
Tönning is a historic town in northern Germany’s Schleswig-Holstein region, known for its strategic location on the Eider River and its former role as a fortified port.
-
B.
Rudersberg
Rudersberg is a small municipality in the German state of Baden-Württemberg, situated in the Rems-Murr district near the city of Stuttgart.
-
C.
Kronshagen
Kronshagen is a small municipality in the German state of Schleswig-Holstein, located near the city of Kiel.
-
D.
Rolfshagen
Rolfshagen is a locality in northern Germany historically notable as the place where Charles Frederick, Duke of Holstein-Gottorp, died.
-
E.
Traneberg
Traneberg is a residential district in western Stockholm, Sweden, known for its mid-20th-century housing and proximity to Lake Mälaren.
- 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_69e11e58662081909ae346ab384514ca |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15f33c9cc819086d098f36e4121dc |
completed | April 29, 2026, 1:30 a.m. |
Created at: April 16, 2026, 8:51 p.m.