Triple
T12594647
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nikkō National Park |
E300702
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Kegon Falls |
E884579
|
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: Kegon Falls | Statement: [Nikkō National Park, contains, Kegon Falls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kegon Falls Context triple: [Nikkō National Park, contains, Kegon Falls]
-
A.
Kegon Falls
chosen
Kegon Falls is one of Japan’s most famous and scenic waterfalls, located near Lake Chūzenji in the mountainous area of Nikkō, Tochigi Prefecture.
-
B.
Nunobiki Falls
Nunobiki Falls is a famous series of scenic waterfalls in Kobe, Japan, celebrated for their natural beauty and cultural significance.
-
C.
Otodome Falls
Otodome Falls is a picturesque waterfall near Mount Fuji in Shizuoka Prefecture, Japan, renowned for its dramatic twin cascades and scenic natural surroundings.
-
D.
Otowa Waterfall
Otowa Waterfall is a famous sacred spring at Kyoto’s Kiyomizu-dera temple where visitors drink from three separate streams believed to grant health, longevity, and academic success.
-
E.
Ryūzu Falls
Ryūzu Falls is a scenic, dragon-shaped waterfall located in the mountainous hot-spring and lake region of Nikkō in Tochigi Prefecture, 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954cde3c0819094e74413d6dcf548 |
completed | April 10, 2026, 7:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f65ec49af881908abb948567b82b74 |
completed | May 2, 2026, 8:29 p.m. |
Created at: April 9, 2026, 5:08 p.m.