Triple
T13461269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Grube Samson |
E311371
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Sankt Andreasberg |
E79399
|
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: Sankt Andreasberg | Statement: [Grube Samson, locatedIn, Sankt Andreasberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sankt Andreasberg Context triple: [Grube Samson, locatedIn, Sankt Andreasberg]
-
A.
Sankt Andreasberg
chosen
Sankt Andreasberg is a historic former mining town and popular mountain resort in the Upper Harz region of central Germany.
-
B.
Wilseder Berg
Wilseder Berg is a prominent hill and popular viewpoint in northern Germany, known for its scenic heathland landscapes within the Lüneburg Heath region.
-
C.
Altlandsberg
Altlandsberg is a small historic town in the Märkisch-Oderland district of Brandenburg, Germany, located just east of Berlin.
-
D.
Deutschlandsberg
Deutschlandsberg is a small Austrian town in the southwest of the state of Styria, known for its surrounding vineyards, castle, and scenic hilly landscape.
-
E.
Festungsberg
Festungsberg is a prominent hill in Salzburg, Austria, best known as the site of the medieval Hohensalzburg Fortress overlooking the city.
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf0d95fc81909d9f73d5315dc7b4 |
completed | April 12, 2026, 2:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f739a2c75c819093765eb9d0d2377e |
completed | May 3, 2026, 12:03 p.m. |
Created at: April 9, 2026, 9:41 p.m.