Triple
T10848356
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grosser Arber |
E256074
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Bodenmais |
E813687
|
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: Bodenmais | Statement: [Grosser Arber, nearbySettlement, Bodenmais]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bodenmais Context triple: [Grosser Arber, nearbySettlement, Bodenmais]
-
A.
Bodenmais
chosen
Bodenmais is a Bavarian spa and holiday resort town in the Bavarian Forest of Germany, known for its glassmaking tradition and outdoor recreation.
-
B.
Todenfeld
Todenfeld is a village and district of the town of Rheinbach in the Rhein-Sieg-Kreis region of North Rhine-Westphalia, Germany.
-
C.
Gerlosbach
Gerlosbach is a mountain river in Tyrol, Austria, that flows through the Zillertal Alps before joining the Ziller.
-
D.
Brenkhausen
Brenkhausen is a village and district of the town of Höxter in North Rhine-Westphalia, Germany.
-
E.
Landensberg
Landensberg is a small municipality in the Bavarian region of southern Germany.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75114ca988190a0e730131adb2df0 |
completed | April 9, 2026, 7:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69dff7cc0d648190afb0ce80bac7f3dc |
completed | April 15, 2026, 8:40 p.m. |
Created at: April 8, 2026, 9:20 p.m.