Triple
T19474987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 東郷神社 |
E487221
|
entity |
| Predicate | hasDeity |
P5606
|
FINISHED |
| Object | 東郷平八郎命 |
—
|
NE NERFINISHED |
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: 東郷平八郎命 | Statement: [東郷神社, hasDeity, 東郷平八郎命]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 東郷平八郎命 Context triple: [東郷神社, hasDeity, 東郷平八郎命]
-
A.
東郷 平八郎
chosen
東郷 平八郎 was a famed Japanese admiral of the Imperial Japanese Navy, best known for leading Japan to victory over Russia in the Battle of Tsushima during the Russo-Japanese War.
-
B.
Ōkuma Shigenobu
Ōkuma Shigenobu was a prominent Japanese statesman of the Meiji era who served twice as prime minister and played a key role in Japan’s modernization and constitutional government.
-
C.
樺山資紀
樺山資紀 was a Meiji-era Japanese naval officer and statesman who served as the first Governor-General of Taiwan and later as Minister of the Navy.
-
D.
Shigenori Tōgō
Shigenori Tōgō was a Japanese diplomat and politician who served as foreign minister during World War II and was later convicted as a Class A war criminal.
-
E.
Saigō Tanomo
Saigō Tanomo was a senior Aizu domain retainer and military leader during Japan’s late Edo period, known for his role in the Boshin War and the defense of Aizu.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8d924388190b847cb15bb3d0aff |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e633f126988190890ff8e5730e4ad3 |
completed | April 20, 2026, 2:10 p.m. |
Created at: April 10, 2026, 1:39 p.m.