Triple
T15729294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akan Onsen |
E381298
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Mount Oakan |
E374539
|
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: Mount Oakan | Statement: [Akan Onsen, near, Mount Oakan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Oakan Context triple: [Akan Onsen, near, Mount Oakan]
-
A.
Mount Oakan
chosen
Mount Oakan is an active stratovolcano on Japan’s northern island of Hokkaido, known for its conical shape and scenic forests and lakes.
-
B.
Mount Rosea
Mount Rosea is a prominent sandstone peak and popular hiking destination within Victoria, Australia’s Grampians mountain range.
-
C.
Mount Doris
Mount Doris is a lesser-known peak in Tasmania’s Cradle Mountain–Lake St Clair National Park, accessible via the famous Overland Track and valued by bushwalkers for its alpine scenery and views.
-
D.
Mount Morris
Mount Morris is a small city in Genesee County, Michigan, located near Flint and known as a residential community with local schools, parks, and small businesses.
-
E.
Mount Oread
Mount Oread is the prominent hill in Lawrence, Kansas that serves as the main site of the University of Kansas campus.
- 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_69d86d9cdb648190bf3171be0bd7d872 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04fb4cc0081909efe330339474017 |
completed | April 16, 2026, 2:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82fcb4e4819097bd0591bbcc3b71 |
completed | May 9, 2026, 6:54 p.m. |
Created at: April 10, 2026, 4:46 a.m.