Triple
T22631372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | B 96 road |
E558561
|
entity |
| Predicate | hasTerminus |
P388
|
FINISHED |
| Object | Rügen |
—
|
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: Rügen | Statement: [B 96 road, hasTerminus, Rügen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rügen Context triple: [B 96 road, hasTerminus, Rügen]
-
A.
Rügen
chosen
Rügen is Germany’s largest island, known for its chalk cliffs, seaside resorts, and beaches along the Baltic Sea coast.
-
B.
Hiddensee
Hiddensee is a car-free German Baltic Sea island known for its unspoiled nature, sandy beaches, and role as a tranquil holiday destination west of Rügen.
-
C.
Hiddensee
Hiddensee is a novel by Gregory Maguire that reimagines the backstory of the Nutcracker and its mysterious creator in a dark, folkloric fantasy.
-
D.
Island of Usedom
The Island of Usedom is a Baltic Sea island shared by Germany and Poland, renowned for its long sandy beaches, seaside resorts, and status as a popular holiday destination.
-
E.
Bornholm
Bornholm is a Danish island known for its rocky coastline, medieval ruins, and picturesque fishing villages in the Baltic Sea.
- 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_69e245467d9881908d6985bd0db7a1f1 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17009ecb0819082f94505b0e2c5b8 |
completed | April 29, 2026, 2:42 a.m. |
Created at: April 17, 2026, 3:02 p.m.