Triple
T11840777
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kūkai |
E281645
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Kūkai |
E355588
|
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: Kūkai | Statement: [Kūkai, name, Kūkai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kūkai Context triple: [Kūkai, name, Kūkai]
-
A.
Kūkai
chosen
Kūkai was a Japanese Buddhist monk, scholar, poet, and founder of the Shingon (esoteric) school of Buddhism, revered as one of Japan’s most important religious figures.
-
B.
Raikō-tō
Raikō-tō is the Japanese name for Raikoke, an uninhabited volcanic island in Russia’s Kuril Islands chain known for its explosive eruptions.
-
C.
Mount Tarumae
Mount Tarumae is an active stratovolcano in Hokkaido, Japan, known for its lava dome and scenic hiking routes overlooking Lake Shikotsu.
-
D.
Kita-dake
Kita-dake, also known as Mount Kita, is Japan's second-highest mountain and a prominent peak in the Akaishi (Southern Alps) range, popular with hikers and mountaineers.
-
E.
Daisetsuzan
Daisetsuzan is a vast mountainous region in central Hokkaido, Japan, renowned for its volcanic peaks, alpine scenery, and rich wildlife.
- 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_69d6ab276f8c8190b1966a0ef11349ac |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a658f918819092c2db05fe2ab0ce |
completed | April 10, 2026, 7:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f1678668ac81909bddf67e8c176757 |
completed | April 29, 2026, 2:05 a.m. |
Created at: April 8, 2026, 9:43 p.m.