Triple
T17370901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hole |
E422310
|
entity |
| Predicate | hasGeographicFeature |
P940
|
FINISHED |
| Object | Krokskogen |
—
|
NE ONNED1 |
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: Krokskogen | Statement: [Hole, hasGeographicFeature, Krokskogen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Krokskogen Context triple: [Hole, hasGeographicFeature, Krokskogen]
-
A.
Krokskogen
chosen
Krokskogen is a large forested area and popular outdoor recreation region in southeastern Norway, known for its hiking and skiing trails between Oslo and the Ringerike district.
-
B.
Kvamskogen
Kvamskogen is a popular mountainous recreational area in western Norway known for its ski resorts, cabins, and outdoor activities.
-
C.
Leirskogen
Leirskogen is a small rural village located in the municipality of Sør-Aurdal in Innlandet county, Norway.
-
D.
Trollskogen
Trollskogen is a coastal nature reserve and windswept pine forest on the island of Öland in Sweden, known for its twisted trees, ancient remains, and scenic hiking trails.
-
E.
Bogleråsen
Bogleråsen is a residential neighborhood located in the Østensjø borough of Oslo, Norway.
- 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_69d889d6535c81908be333c01deaec4e |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a68ff448190b505861e56df5b6d |
completed | April 19, 2026, 2:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a019568a27c8190af1bbe6db75f3e6f |
in_progress | May 11, 2026, 8:38 a.m. |
Created at: April 10, 2026, 5:44 a.m.