Triple
T10760445
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nikko |
E253811
|
entity |
| Predicate | hasMountain |
P10602
|
FINISHED |
| Object | Mount Nantai |
E304336
|
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 Nantai | Statement: [Nikko, hasMountain, Mount Nantai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Nantai Context triple: [Nikko, hasMountain, Mount Nantai]
-
A.
Mount Nantai
chosen
Mount Nantai is a prominent stratovolcano in Japan known as a sacred mountain of Shinto and a scenic landmark near Lake Chūzenji in Nikkō.
-
B.
Mount Tsurumi
Mount Tsurumi is a volcanic mountain in Ōita Prefecture, Japan, known for its panoramic views, seasonal foliage, and ropeway access from the hot spring resort city of Beppu.
-
C.
Mount Suiro
Mount Suiro is the tallest mountain on Biliran Island in the Philippines, forming a prominent part of the island’s volcanic landscape.
-
D.
Mount Goryu
Mount Goryu is a prominent peak in Japan’s Northern Alps, known for its ski resorts and alpine hiking within the Hakuba Valley area.
-
E.
Mount Sankaku
Mount Sankaku is a small, popular hiking and viewpoint mountain located in Nishi-ku, Sapporo, Japan.
- 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_69d6aa5f54f4819082d0bbcb6f8797e6 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d731a14c7481909c6f4f9b15dc130f |
completed | April 9, 2026, 4:57 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5d2d717888190b7e455d006d01033 |
completed | April 20, 2026, 7:16 a.m. |
Created at: April 8, 2026, 9:16 p.m.