Triple
T17600172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dagmar of Bohemia |
E428675
|
entity |
| Predicate | placeOfDeath |
P21
|
FINISHED |
| Object | Ribe |
—
|
NE NERFINISHED |
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: Ribe | Statement: [Dagmar of Bohemia, placeOfDeath, Ribe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ribe Context triple: [Dagmar of Bohemia, placeOfDeath, Ribe]
-
A.
Ribe
chosen
Ribe is the oldest town in Denmark, known for its well-preserved medieval center and Viking heritage.
-
B.
Ribe
Ribe is one of the traditional settlements or sub-groups associated with the Mijikenda people of the Kenyan coast, known for its cultural and historical significance.
-
C.
Havelberg
Havelberg is a small historic town in Saxony-Anhalt, Germany, known for its medieval cathedral and location at the confluence of the Havel and Elbe rivers.
-
D.
Viborg
Viborg is one of Denmark’s oldest cities, historically significant as a medieval political and religious center on the Jutland peninsula.
-
E.
Viborg
Viborg is the Swedish name for the historic Karelian city of Vyborg, located near the Finnish border on the Gulf of Finland.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c4812d48190bf8e899fa8f7fbe4 |
completed | April 19, 2026, 5:46 a.m. |
Created at: April 10, 2026, 5:51 a.m.