Triple
T10838609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hōei eruption |
E255827
|
entity |
| Predicate | ashFall |
P45311
|
FINISHED |
| Object | Edo |
E69445
|
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: Edo | Statement: [Hōei eruption, ashFall, Edo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Edo Context triple: [Hōei eruption, ashFall, Edo]
-
A.
Edo
Edo is a historic city in present-day southern Nigeria, renowned as the political and cultural center of the former Benin Kingdom and its sophisticated art and urban civilization.
-
B.
Edo
chosen
Edo was the historical name of Japan’s capital during the Tokugawa shogunate, a major political and cultural center that later became modern Tokyo.
-
C.
Kamakura
Kamakura is a historic coastal city in Japan renowned for its Great Buddha statue, numerous temples and shrines, and role as the political center of the Kamakura shogunate.
-
D.
Meijō
Meijō is the Japanese name for Nagoya Castle, a historic and iconic samurai-era fortress in Nagoya, Japan.
-
E.
Dazaifu
Dazaifu is a historic city in Fukuoka Prefecture, Japan, known for its ancient government offices and the famous Dazaifu Tenmangū shrine dedicated to scholar-statesman Sugawara no Michizane.
- 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d747002b3081908726901ee83d8f38 |
completed | April 9, 2026, 6:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69deb139072081908a67e76a83575c32 |
completed | April 14, 2026, 9:27 p.m. |
Created at: April 8, 2026, 9:19 p.m.