Triple
T9639110
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nyborg |
E233013
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Nyborg Castle |
E676679
|
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: Nyborg Castle | Statement: [Nyborg, contains, Nyborg Castle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nyborg Castle Context triple: [Nyborg, contains, Nyborg Castle]
-
A.
Nyborg Castle
chosen
Nyborg Castle is a historic medieval fortress and former royal residence located in the town of Nyborg on the Danish island of Funen.
-
B.
Vordingborg Castle
Vordingborg Castle is a historic medieval fortress in Denmark, closely associated with the royal power and military campaigns of King Valdemar II.
-
C.
Sønderborg Castle
Sønderborg Castle is a historic Danish fortress and former royal residence on the island of Als, notable for its role in Denmark’s royal and military history.
-
D.
Søborg Castle
Søborg Castle was a medieval stronghold in northern Zealand, Denmark, historically significant as a royal residence and fortress.
-
E.
Kalundborg Castle
Kalundborg Castle was a significant medieval royal stronghold in the Danish town of Kalundborg, historically used as a residence and fortress by Danish monarchs.
- 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_69ca848a5a908190aad251f4137b0c3a |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9b532aa4819087b56be6f5635126 |
completed | April 1, 2026, 10:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d190eaac248190a19be2ceb333372f |
completed | April 4, 2026, 10:30 p.m. |
Created at: March 30, 2026, 8:12 p.m.