Triple
T15077064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sund municipality |
E380031
|
entity |
| Predicate | includedIslands |
P27557
|
FINISHED |
| Object | southern part of Sotra |
—
|
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: southern part of Sotra | Statement: [Sund municipality, includedIslands, southern part of Sotra]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includedIslands Context triple: [Sund municipality, includedIslands, southern part of Sotra]
-
A.
includesArchipelago
Indicates that one geographic entity contains or encompasses an archipelago within its area or jurisdiction.
-
B.
composedOfIslands
Indicates that something is geographically formed or constituted by multiple islands.
-
C.
associatedIsland
chosen
Indicates that one entity is related to or connected with a particular island in some relevant way.
-
D.
includeRemoteIslands
Indicates whether the relationship or operation should also cover or account for remote islands in addition to the main area or entities.
-
E.
islandBased
Indicates that something is located on, originates from, or is primarily associated with an island.
- 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_69d85cd7683881908d405c1b5d7b4f7f |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69dff7fe5a208190823900b25e298dab |
completed | April 15, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69deb9645b9c8190a5712456dbd78029 |
completed | April 14, 2026, 10:02 p.m. |
Created at: April 10, 2026, 3:03 a.m.