Triple
T736562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kaunas |
E14945
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Rostock |
E56817
|
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: Rostock | Statement: [Kaunas, hasTwinTown, Rostock]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rostock Context triple: [Kaunas, hasTwinTown, Rostock]
-
A.
Rostock
chosen
Rostock is a historic Hanseatic city in northern Germany known for its significant seaport on the Baltic Sea and its long maritime and trading tradition.
-
B.
Lübeck
Lübeck is a historic Hanseatic city in northern Germany renowned for its medieval architecture and long-standing role as a key trading hub on the Baltic Sea.
-
C.
Wismar
Wismar is a historic Hanseatic port city on Germany’s Baltic Sea coast, known for its well-preserved medieval architecture and UNESCO-listed old town.
-
D.
Schwerin
Schwerin is a historic city in northern Germany known for its picturesque lakeside setting and landmark Schwerin Castle.
-
E.
Greifswald
Greifswald is a historic Hanseatic university city in northeastern Germany, located near the Baltic Sea.
- 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_69a4934d9930819099eed80096b0597d |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a5da30b88190afbd12ae6109cc1b |
completed | March 1, 2026, 8:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad3072c3a881908c33159cdd55ae0b |
completed | March 8, 2026, 8:16 a.m. |
Created at: March 1, 2026, 7:37 p.m.