Triple
T20456625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Erkrath |
E501804
|
entity |
| Predicate | locatedOnRiver |
P165
|
FINISHED |
| Object | Düssel |
—
|
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: Düssel | Statement: [Erkrath, locatedOnRiver, Düssel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Düssel Context triple: [Erkrath, locatedOnRiver, Düssel]
-
A.
Düssel
chosen
Düssel is a small village and district within the town of Wülfrath in North Rhine-Westphalia, Germany.
-
B.
Dürrnberg
Dürrnberg is a mountain area in the Austrian Alps known for its historic salt mines and scenic landscapes near the town of Hallein.
-
C.
Seßlach
Seßlach is a small, well-preserved medieval town in northern Bavaria, Germany, known for its intact city walls and historic half-timbered houses.
-
D.
Wollerau
Wollerau is an affluent municipality on the shores of Lake Zurich in the Swiss canton of Schwyz, known for its low taxes and as a residence of several wealthy individuals.
-
E.
Wiedlisbach
Wiedlisbach is a historic small town in the canton of Bern, Switzerland, known for its well-preserved medieval old town and former status as a fortified market settlement.
- 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_69e0b4ad4940819098cf2ff6413574e5 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e696a1b03c8190984d9db6d3251308 |
completed | April 20, 2026, 9:12 p.m. |
Created at: April 16, 2026, 11:32 a.m.