Triple
T2316252
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mount Fuji |
E51069
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object | Fujisan |
E51069
|
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: Fujisan | Statement: [Mount Fuji, romanization, Fujisan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fujisan Context triple: [Mount Fuji, romanization, Fujisan]
-
A.
Mount Fuji
chosen
Mount Fuji is Japan’s iconic, snow-capped stratovolcano and highest peak, renowned for its nearly symmetrical cone and cultural significance.
-
B.
Mount Akagi
Mount Akagi is a prominent volcanic mountain in Japan’s Gunma Prefecture, known for its caldera lakes, scenic hiking trails, and cultural significance in local folklore.
-
C.
Mount Rokko
Mount Rokko is a prominent mountain range near Kobe, Japan, known for its panoramic night views, hiking trails, and recreational facilities.
-
D.
Takamagahara
Takamagahara is the heavenly realm in Shinto mythology, home of the kami and the divine seat of celestial authority.
-
E.
Mount Hachiman
Mount Hachiman is a scenic hill in Ōmihachiman, Shiga Prefecture, known for its historical significance, hiking trails, and panoramic views over the city and Lake Biwa.
- 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_69a88b074b908190ae983dbca7757d88 |
completed | March 4, 2026, 7:41 p.m. |
| NER | Named-entity recognition | batch_69abc61e72508190b335cda2c7fef130 |
completed | March 7, 2026, 6:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae896236f08190b3874854279bbdf7 |
completed | March 9, 2026, 8:48 a.m. |
Created at: March 4, 2026, 7:49 p.m.