Triple
T14089864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Úpa River |
E339098
|
entity |
| Predicate | flowsThrough |
P225
|
FINISHED |
| Object | Trutnov |
E257720
|
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: Trutnov | Statement: [Úpa River, flowsThrough, Trutnov]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Trutnov Context triple: [Úpa River, flowsThrough, Trutnov]
-
A.
Trutnov
chosen
Trutnov is a town in the Czech Republic known as a gateway to the eastern Krkonoše (Giant Mountains) region and for its historical center and industrial heritage.
-
B.
Chrudim
Chrudim is a historic town in the Pardubice Region of the Czech Republic, known for its well-preserved medieval center and cultural heritage.
-
C.
Tišnov
Tišnov is a small historic town in the South Moravian Region of the Czech Republic, located northwest of Brno.
-
D.
Třebíč
Třebíč is a historic town in the Vysočina Region of the Czech Republic, known for its well-preserved Jewish Quarter and Basilica of St. Procopius, both UNESCO World Heritage Sites.
-
E.
Přerov
Přerov is a city in the Olomouc Region of the Czech Republic, known as an important industrial and transport hub on the Bečva River.
- 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_69d81c687b0c819087fd9ed4198403f8 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de5ee3213c8190af2853a2a5b302a2 |
completed | April 14, 2026, 3:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fee5dc9b908190b1d7583810dc9c41 |
completed | May 9, 2026, 7:44 a.m. |
Created at: April 9, 2026, 10:21 p.m.