Triple
T18327000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vammafossen |
E439036
|
entity |
| Predicate | watercourse |
P415
|
FINISHED |
| Object | Glomma watercourse |
E96298
|
NE 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: Glomma watercourse | Statement: [Vammafossen, watercourse, Glomma watercourse]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Glomma watercourse Context triple: [Vammafossen, watercourse, Glomma watercourse]
-
A.
Glomma
chosen
Glomma is Norway’s longest and largest river, flowing through Eastern Norway before emptying into the Oslofjord.
-
B.
Glomma valley
Glomma valley is a river valley in Norway shaped by and named after the country’s longest river, the Glåma (Glomma).
-
C.
Drammenselva
Drammenselva is a major river in southeastern Norway known for its historical timber floating, hydroelectric power production, and salmon fishing.
-
D.
Akerselva river
Akerselva river is a historically significant river in Oslo, Norway, known for its former industrial sites, scenic walking paths, and role as a natural boundary between city districts.
-
E.
Saltdalselva
Saltdalselva is a river in Nordland county, Norway, known for flowing through the Saltdal valley and offering notable salmon fishing and scenic natural landscapes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d8b916a2d081909e249e4902f6aad9 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e50aab3e7c81909b1c0a688707dfd6 |
completed | April 19, 2026, 5:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0787a351c48190ac9497506fe738fd |
completed | May 15, 2026, 8:52 p.m. |
Created at: April 10, 2026, 10:36 a.m.