Triple
T25132563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bervie Water |
E629563
|
entity |
| Predicate | hasCoastalOutlet |
P212
|
FINISHED |
| Object |
North Sea at Inverbervie
The North Sea at Inverbervie is a stretch of the North Sea coastline on Scotland’s east coast where the Bervie Water river meets the sea near the town of Inverbervie.
|
E1667105
|
NE FINISHED |
How this triple was built (3 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]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: North Sea at Inverbervie Triple: [Bervie Water, hasCoastalOutlet, North Sea at Inverbervie]
Generated description
The North Sea at Inverbervie is a stretch of the North Sea coastline on Scotland’s east coast where the Bervie Water river meets the sea near the town of 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 (6 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. |
| NED1 | Entity disambiguation (via context triple) | batch_6a105cfc4b808190bd6f40efb5a97817 |
completed | May 22, 2026, 1:41 p.m. |
| NEDg | Description generation | batch_6a105df4d07881909cb98f27deeb0adb |
completed | May 22, 2026, 1:45 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a105f4ef2648190a3b26415b711b171 |
completed | May 22, 2026, 1:51 p.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
Created at: April 18, 2026, 6:28 a.m.