Triple
T14196160
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yoshida Shōin |
E351839
|
entity |
| Predicate | taughtAt |
P1203
|
FINISHED |
| Object | Shōka Sonjuku |
E1088646
|
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: Shōka Sonjuku | Statement: [Yoshida Shōin, taughtAt, Shōka Sonjuku]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shōka Sonjuku Context triple: [Yoshida Shōin, taughtAt, Shōka Sonjuku]
-
A.
Shōka Sonjuku
chosen
Shōka Sonjuku was a small but influential private academy in late Edo-period Japan that educated many key figures who later led the Meiji Restoration.
-
B.
Shimbun Akahata
Shimbun Akahata is the official newspaper of Japan’s Communist Party, known for its leftist political coverage and advocacy.
-
C.
Kōtaigō Shōken
Kōtaigō Shōken is the posthumous title of Empress Haruko, the consort of Emperor Meiji and Japan’s first modern empress.
-
D.
Kamiyama Sojin
Kamiyama Sojin was a Japanese actor active in early 20th-century cinema, known for his roles in both Japanese and American silent and early sound films.
-
E.
Kakuji Kakuta
Kakuji Kakuta was a senior Imperial Japanese Navy admiral and air commander during World War II, known for leading Japanese forces in several major Pacific campaigns.
- 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_69d827894ac0819097803e57f3227b23 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61e1fbd48190a4864fa4443f8f29 |
completed | April 14, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4674da8881909dc6c1c8a36cf78e |
completed | May 8, 2026, 2:12 a.m. |
Created at: April 10, 2026, 1:04 a.m.