Triple
T15000627
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gdynia Śródmieście SKM station |
E374076
|
entity |
| Predicate | connectsTo |
P845
|
FINISHED |
| Object | Wejherowo |
—
|
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: Wejherowo | Statement: [Gdynia Śródmieście SKM station, connectsTo, Wejherowo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wejherowo Context triple: [Gdynia Śródmieście SKM station, connectsTo, Wejherowo]
-
A.
Wejherowo
chosen
Wejherowo is a historic town in northern Poland known for its baroque Calvary complex and role as a local cultural and administrative center.
-
B.
Grodkowo
Grodkowo is a settlement in northern Poland located within the Warmian-Masurian Voivodeship, a region known for its lakes and natural landscapes.
-
C.
Braniewo
Braniewo is a historic town in northern Poland near the Baltic coast, known as one of the oldest urban centers in the Warmia region.
-
D.
Zułowo
Zułowo is a village in present-day Lithuania best known as the birthplace of Józef Piłsudski, a key figure in Poland’s struggle for independence.
-
E.
Zembrzyce
Zembrzyce is a village in southern Poland that serves as the local administrative and cultural hub of its surrounding rural area.
- 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_69d85ccc84388190aa151e5173370c8d |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69ded72fec948190b1c9705538c57976 |
completed | April 15, 2026, 12:09 a.m. |
Created at: April 10, 2026, 2:54 a.m.