Triple
T17320023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 軍需大臣 |
E420534
|
entity |
| Predicate | usedIn |
P98
|
FINISHED |
| Object | 大日本帝国 |
E643007
|
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: 大日本帝国 | Statement: [軍需大臣, usedIn, 大日本帝国]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 大日本帝国 Context triple: [軍需大臣, usedIn, 大日本帝国]
-
A.
大日本帝国
chosen
大日本帝国は、明治維新後から第二次世界大戦終結まで続いた、日本の天皇制を中心とする近代立憲君主国家である。
-
B.
Imperial Japan
Imperial Japan was the militaristic empire that dominated East Asia in the early 20th century and served as a principal Axis power in World War II, pursuing aggressive expansion and engaging in major conflicts with the Allied nations.
-
C.
大和
大和 is the historical Japanese name for the ancient province and cultural heartland that gave rise to the early Japanese state and imperial court.
-
D.
陸奥国
陸奥国 was an expansive historical province in northeastern Honshū, Japan, encompassing much of the modern Tōhoku region.
-
E.
Nippon Eitaigura
Nippon Eitaigura is a late 17th-century Japanese ukiyo-zōshi story collection by Ihara Saikaku that vividly portrays the lives and fortunes of Osaka merchants.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439a066b481908e8aee1885809eba |
completed | April 19, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c483e988190a481b4c487f79329 |
completed | May 11, 2026, 7:59 a.m. |
Created at: April 10, 2026, 5:43 a.m.