Triple
T7316757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Flensburg |
E168430
|
entity |
| Predicate | twinTown |
P1072
|
FINISHED |
| Object | Tønder |
E635019
|
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: Tønder | Statement: [Flensburg, twinTown, Tønder]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tønder Context triple: [Flensburg, twinTown, Tønder]
-
A.
Tønder
chosen
Tønder is a historic market town in southern Denmark near the German border, known for its well-preserved old town and cultural heritage.
-
B.
Vejle
Vejle is a Danish city known for its scenic fjord setting, rolling hills, and role as a regional commercial and transportation hub in southeastern Jutland.
-
C.
Næstved
Næstved is a historic market town and commercial center in southern Denmark, located on the island of Zealand.
-
D.
Hjørring
Hjørring is a historic town in northern Denmark known as one of the oldest settlements in the Vendsyssel region and a local commercial and cultural center.
-
E.
Kolding
Kolding is a historic Danish city in Southern Jutland known for Koldinghus Castle, its fjord-side location, and its role as a regional cultural and educational center.
- 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_69c68a5251508190ad68df4151cfeb04 |
completed | March 27, 2026, 1:46 p.m. |
| NER | Named-entity recognition | batch_69c6ef162d488190bf1c63b71b20a294 |
completed | March 27, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c810c6617c8190b4b37466e32c71c0 |
completed | March 28, 2026, 5:32 p.m. |
Created at: March 27, 2026, 3:02 p.m.