Triple
T14089887
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Úpa River |
E339098
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Sněžka |
E425049
|
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: Sněžka | Statement: [Úpa River, near, Sněžka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sněžka Context triple: [Úpa River, near, Sněžka]
-
A.
Sněžka
chosen
Sněžka is the highest mountain in the Czech Republic, located on the border with Poland in the Krkonoše range.
-
B.
Lysá hora
Lysá hora is the highest peak of the Moravian-Silesian Beskids in the Czech Republic, known for its panoramic views and popular hiking and skiing routes.
-
C.
Ještěd Mountain
Ještěd Mountain is a prominent peak in the Czech Republic known for its distinctive futuristic hotel and television tower that dominates the skyline near the city of Liberec.
-
D.
Snježnik mountain
Snježnik mountain is a prominent peak in Croatia’s Dinaric Alps, known for its rugged karst landscape, rich biodiversity, and panoramic views within the Risnjak National Park region.
-
E.
Wildspitze
Wildspitze is a prominent mountain in the Ötztal Alps of Tyrol, Austria, known as one of the country's highest and most popular alpine climbing peaks.
- 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_69fcd0a7aab88190949cf1fd8e11b050 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:21 p.m.