Triple
T8066193
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | District of Mittelsachsen |
E188248
|
entity |
| Predicate | hasCapital |
P204
|
FINISHED |
| Object | Freiberg |
E123043
|
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: Freiberg | Statement: [District of Mittelsachsen, hasCapital, Freiberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Freiberg Context triple: [District of Mittelsachsen, hasCapital, Freiberg]
-
A.
Freiberg
chosen
Freiberg is a historic mining town in eastern Germany renowned for its silver mining heritage and well-preserved medieval architecture.
-
B.
Reichenberg
Reichenberg is the former German name for the city of Liberec, a major urban center in the northern Czech Republic near the border with Germany and Poland.
-
C.
Riesa
Riesa is a town in the German state of Saxony, situated on the Elbe River and known historically as an important regional railway and industrial center.
-
D.
Lankwitz
Lankwitz is a residential locality in the southwestern part of Berlin, known for its quiet neighborhoods, green spaces, and mix of historic and modern architecture.
-
E.
Bischofswerda
Bischofswerda is a small town in the Saxony region of eastern Germany, known as a local commercial and transport hub near the city of Dresden.
- 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_69ca82b42674819086840efea12478e5 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3ff5547c8190a7ec5958a23e302f |
completed | March 31, 2026, 3:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cd947cf7a881908b45cf262887da86 |
completed | April 1, 2026, 9:56 p.m. |
Created at: March 30, 2026, 5:26 p.m.