Triple
T9445721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duchess of Bohemia |
E227758
|
entity |
| Predicate | usedIn |
P98
|
FINISHED |
| Object | Bohemia |
E30190
|
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: Bohemia | Statement: [Duchess of Bohemia, usedIn, Bohemia]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bohemia Context triple: [Duchess of Bohemia, usedIn, Bohemia]
-
A.
Bohemia
chosen
Bohemia is a historical region in the western part of the modern Czech Republic, long a cultural and political center of Central Europe.
-
B.
Bohemia
Bohemia is a hamlet in Suffolk County, New York, known for its residential character and proximity to Long Island’s south shore communities.
-
C.
Moravia
Moravia is a historical region in the eastern part of the Czech Republic, known for its distinct cultural heritage, wine production, and major cities such as Brno and Olomouc.
-
D.
Moravia
Moravia is a canton in Costa Rica known for its suburban character and proximity to the capital city of San José.
-
E.
Czech lands
The Czech lands are the historical regions of Bohemia, Moravia, and Czech Silesia that form the core territory of today’s Czech Republic.
- 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_69ca843884488190ad6cbe0153088234 |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7f33deb88190bc74968575963ac4 |
completed | April 1, 2026, 8:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d11026b8688190b958ca65dae2d588 |
completed | April 4, 2026, 1:20 p.m. |
Created at: March 30, 2026, 7:51 p.m.