Triple
T8235324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tōshō |
E192390
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object | Tōshō |
E192390
|
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: Tōshō | Statement: [Tōshō, romanization, Tōshō]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tōshō Context triple: [Tōshō, romanization, Tōshō]
-
A.
Tōshō
chosen
Tōshō is the commonly used Japanese abbreviation for the Tokyo Stock Exchange, one of the world’s largest and most influential stock markets.
-
B.
Tōshō Daigongen
Tōshō Daigongen is the deified title of Tokugawa Ieyasu, venerated as a protective Shinto deity and founder of the Tokugawa shogunate.
-
C.
Hachiman
Hachiman is a major Shinto deity revered as the god of war and the divine protector of Japan and its people, especially warriors.
-
D.
Meiji Jingū
Meiji Jingū is a major Shinto shrine in Tokyo dedicated to the deified spirits of Emperor Meiji and Empress Shōken, renowned for its tranquil forested grounds amid the city.
-
E.
Hōshin Myōju
Hōshin Myōju was the wife of the famed Japanese tea master Sen no Rikyū, associated with the cultural milieu surrounding the development of wabi-cha tea ceremony aesthetics in the late Sengoku period.
- 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_69ca82dc8f148190a2c75a98501a7b91 |
completed | March 30, 2026, 2:04 p.m. |
| NER | Named-entity recognition | batch_69cb782931848190bcc54622f34e06a7 |
completed | March 31, 2026, 7:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cde74c4e6c8190a426139f71689a3e |
completed | April 2, 2026, 3:49 a.m. |
Created at: March 30, 2026, 5:46 p.m.