Triple
T20070010
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Most Tumski |
E499707
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Wyspa Piasek |
—
|
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: Wyspa Piasek | Statement: [Most Tumski, connects, Wyspa Piasek]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wyspa Piasek Context triple: [Most Tumski, connects, Wyspa Piasek]
-
A.
Wyspa Piasek
chosen
Wyspa Piasek is a river island on the Oder in Wrocław, Poland, known for its historic churches and picturesque riverside setting.
-
B.
Mieleńska Island
Mieleńska Island is an island located within Dąbie Lake in northwestern Poland, known as part of the Szczecin area’s inland water landscape.
-
C.
Wyspa Kępa Mieszczańska
Wyspa Kępa Mieszczańska is a river island in Wrocław, Poland, situated on the Oder and known for its central location, residential areas, and recreational green spaces.
-
D.
Wyspa Bachorska
Wyspa Bachorska is a small Polish island located within Lake Charzykowskie, known for its natural scenery and tranquil surroundings.
-
E.
Dębina Island
Dębina Island is a small island located within Dąbie Lake in northwestern Poland, known for its natural scenery and recreational appeal.
- 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6643798a4819081fa4e71c74b47bc |
completed | April 20, 2026, 5:36 p.m. |
Created at: April 11, 2026, 3:39 p.m.