Triple
T25132563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bervie Water |
E629563
|
entity |
| Predicate | hasCoastalOutlet |
P212
|
FINISHED |
| Object | North Sea at Inverbervie |
—
|
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: North Sea at Inverbervie | Statement: [Bervie Water, hasCoastalOutlet, North Sea at Inverbervie]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCoastalOutlet Context triple: [Bervie Water, hasCoastalOutlet, North Sea at Inverbervie]
-
A.
hasCoastline
Indicates that a geographic entity is bordered by and directly touches a sea or ocean along part of its boundary.
-
B.
hasCoastalRegion
Indicates that a place possesses at least one region that borders or is directly adjacent to a sea or ocean.
-
C.
hasCoastalCharacteristic
Indicates that an entity possesses a feature, quality, or condition specifically related to coastal or shoreline environments.
-
D.
hasCoastlineOn
chosen
Indicates that one entity’s coastline borders or is directly adjacent to a specified body of water.
-
E.
hasCoastalAdjacentArea
Indicates that one area directly borders or is immediately next to a coastal zone.
- 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_69e2ff338250819096ff6c8892804389 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f70e8755a48190931eaa77946f9460 |
completed | May 3, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
Created at: April 18, 2026, 6:28 a.m.