Triple
T15690367
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bømlo Municipality |
E380311
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object |
Lykling
Lykling is an island in western Norway known for its coastal landscape and location within Bømlo Municipality in Vestland county.
|
E1170718
|
NE FINISHED |
How this triple was built (4 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: Lykling | Statement: [Bømlo Municipality, hasIsland, Lykling]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lykling Context triple: [Bømlo Municipality, hasIsland, Lykling]
-
A.
Larkollen
Larkollen is a coastal village in southeastern Norway known for its beaches, holiday homes, and maritime recreation.
-
B.
Suliskongen
Suliskongen is a prominent mountain in the Sulitjelma massif of northern Norway, known as one of the major peaks in the Scandinavian border region between Norway and Sweden.
-
C.
Orlyk
Orlyk is a Ukrainian surname most notably associated with Pylyp Orlyk, an 18th-century Cossack leader and author of one of Europe’s earliest constitutional documents.
-
D.
Byllynge
Byllynge is an English surname most notably associated with Edward Byllynge, a 17th-century colonial proprietor involved in the early governance of New Jersey.
-
E.
Lågen
Lågen is a major river in southeastern Norway that flows through the Gudbrandsdalen valley before joining the Mjøsa lake.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Lykling Triple: [Bømlo Municipality, hasIsland, Lykling]
Generated description
Lykling is an island in western Norway known for its coastal landscape and location within Bømlo Municipality in Vestland county.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lykling Target entity description: Lykling is an island in western Norway known for its coastal landscape and location within Bømlo Municipality in Vestland county.
-
A.
Larkollen
Larkollen is a coastal village in southeastern Norway known for its beaches, holiday homes, and maritime recreation.
-
B.
Suliskongen
Suliskongen is a prominent mountain in the Sulitjelma massif of northern Norway, known as one of the major peaks in the Scandinavian border region between Norway and Sweden.
-
C.
Orlyk
Orlyk is a Ukrainian surname most notably associated with Pylyp Orlyk, an 18th-century Cossack leader and author of one of Europe’s earliest constitutional documents.
-
D.
Byllynge
Byllynge is an English surname most notably associated with Edward Byllynge, a 17th-century colonial proprietor involved in the early governance of New Jersey.
-
E.
Lågen
Lågen is a major river in southeastern Norway that flows through the Gudbrandsdalen valley before joining the Mjøsa lake.
- F. None of above. chosen
Provenance (5 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_69d86d99e860819094b6957cde470f2c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f4e59988190aaf12f6a07c8f0e4 |
completed | April 16, 2026, 2:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff6eebaccc8190a61fb2f9b9bdbcc1 |
completed | May 9, 2026, 5:29 p.m. |
| NEDg | Description generation | batch_69ff6fb61144819085460226d406161d |
completed | May 9, 2026, 5:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff705b1ea08190bf08b99c19715e57 |
completed | May 9, 2026, 5:35 p.m. |
Created at: April 10, 2026, 4:44 a.m.