Triple
T21237672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | White Mountain |
E523387
|
entity |
| Predicate | hasCzechName |
P17790
|
FINISHED |
| Object | Bílá hora |
—
|
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: Bílá hora | Statement: [White Mountain, hasCzechName, Bílá hora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bílá hora Context triple: [White Mountain, hasCzechName, Bílá hora]
-
A.
Bílá Hora
chosen
Bílá Hora is a historic hill and district in Prague best known as the site of the 1620 Battle of White Mountain, a decisive event in Czech and European history.
-
B.
Hlubočky
Hlubočky is a municipality and village in the Olomouc Region of the Czech Republic, known historically for its industrial facilities and proximity to the city of Olomouc.
-
C.
Skalnaté pleso
Skalnaté pleso is a mountain lake in the High Tatras of Slovakia, known as a popular hiking and tourist destination surrounded by alpine scenery.
-
D.
Blaník
Blaník is a Czech play by Václav Kliment Klicpera, best known for drawing on the national legend of the sleeping knights of Mount Blaník.
-
E.
Zátopek
Zátopek is a Czech surname most famously associated with Emil Zátopek, the legendary long-distance runner and four-time Olympic gold medalist.
- 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_69e0b513b89c81908b27147e91368db2 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e735212ad4819082d85f4d4342faf9 |
completed | April 21, 2026, 8:28 a.m. |
Created at: April 16, 2026, 3:46 p.m.