Triple
T18717679
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ghent–Terneuzen Canal |
E457683
|
entity |
| Predicate | openedToSea |
P39201
|
FINISHED |
| Object | via Western Scheldt at Terneuzen |
—
|
LITERAL 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: via Western Scheldt at Terneuzen | Statement: [Ghent–Terneuzen Canal, openedToSea, via Western Scheldt at Terneuzen]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openedToSea Context triple: [Ghent–Terneuzen Canal, openedToSea, via Western Scheldt at Terneuzen]
-
A.
touchesSea
Indicates that one entity is in direct physical contact with the sea or coastline of another entity.
-
B.
enteredOcean
Indicates that an entity moved from land, air, or another medium into the ocean.
-
C.
seaOf
Indicates a relationship where one entity is metaphorically or literally surrounded or filled by another like a vast sea, emphasizing overwhelming abundance or expansiveness.
-
D.
endSea
Indicates that something marks the boundary or termination point of a sea or sea area.
-
E.
outletToSea
chosen
Indicates that a body of water or waterway has a direct opening or connection that leads into the sea.
- 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_69d8d393ba9c8190a8b03b04ddbb0a09 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e56ab8198c8190bf2c4acaeb561970 |
completed | April 19, 2026, 11:52 p.m. |
| PD | Predicate disambiguation | batch_69e478e0889c8190a118d67b200ce8ef |
completed | April 19, 2026, 6:40 a.m. |
Created at: April 10, 2026, 11:50 a.m.