Triple
T38262340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gdynia–Kościerzyna railway line |
E1017959
|
entity |
| Predicate | connectsToBodyOfWaterViaCity |
P181206
|
FINISHED |
| Object | Baltic Sea |
—
|
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: Baltic Sea | Statement: [Gdynia–Kościerzyna railway line, connectsToBodyOfWaterViaCity, Baltic Sea]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsToBodyOfWaterViaCity Context triple: [Gdynia–Kościerzyna railway line, connectsToBodyOfWaterViaCity, Baltic Sea]
-
A.
connectsInlandCityToCoast
Indicates a relationship where a route, link, or infrastructure connects an inland city to a coastal area or city.
-
B.
connectsToBodyOfWaterViaRail
chosen
Indicates that an entity has a rail transport link providing access to a body of water.
-
C.
connectsBodyOfWater
Indicates a relationship where one entity serves as a link or passage between two bodies of water, allowing them to be joined or interact.
-
D.
connectsToBodyOfWaterRegion
Indicates that a region has a direct physical connection or boundary with a body of water.
-
E.
connectsToCoastAt
Indicates that one entity has a direct physical or geographical connection or access to a coastline at the location of another entity.
- F. None of above.
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_69f76de33e4481909099fa812709bd42 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0018cf6ebc8190aee6288788d0067e |
completed | May 10, 2026, 5:34 a.m. |
| PD | Predicate disambiguation | batch_6a001855e8588190a65840485473cf8b |
completed | May 10, 2026, 5:32 a.m. |
Created at: May 3, 2026, 4:30 p.m.