Triple
T8062830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Liberec |
E188165
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Zittau |
E445817
|
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: Zittau | Statement: [Liberec, twinTown, Zittau]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zittau Context triple: [Liberec, twinTown, Zittau]
-
A.
Zittau
chosen
Zittau is a historic town in the southeastern corner of Germany, known for its proximity to both the Czech and Polish borders and its well-preserved medieval architecture.
-
B.
Bautzen
Bautzen is a historic town in eastern Germany known for its well-preserved medieval architecture and as a cultural center of the Sorbian minority.
-
C.
Liebenwalde
Liebenwalde is a small town and municipality in the Oberhavel district of the German state of Brandenburg.
-
D.
Görlitz
Görlitz is a historic city in eastern Germany on the Lusatian Neisse River, known for its well-preserved old town and role as a popular film location.
-
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_69ca82b2f68881908c50560697e210da |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3fce95f08190b803956a20082e95 |
completed | March 31, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccecdfddb08190bfda3bb5c02215d9 |
completed | April 1, 2026, 10:01 a.m. |
Created at: March 30, 2026, 5:26 p.m.