Triple
T14357704
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 伊藤博文 |
E356012
|
entity |
| Predicate | 関連人物 |
P37304
|
FINISHED |
| Object | 山県有朋 |
E41939
|
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: 山県有朋 | Statement: [伊藤博文, 関連人物, 山県有朋]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 山県有朋 Context triple: [伊藤博文, 関連人物, 山県有朋]
-
A.
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.
-
B.
Itō Hirobumi
Itō Hirobumi was a leading Meiji-era Japanese statesman and the country’s first Prime Minister, instrumental in modernizing Japan and drafting its constitution.
-
C.
Yamagata Aritomo
chosen
Yamagata Aritomo was a prominent Meiji-era Japanese military leader and statesman who helped modernize Japan’s army and twice served as Prime Minister.
-
D.
Kido Takayoshi
Kido Takayoshi was a key Japanese statesman and one of the principal architects of the Meiji Restoration who helped modernize Japan’s political and social systems in the late 19th century.
-
E.
Yasuo Yamagata
Yasuo Yamagata was an Imperial Japanese Army officer who led Japanese forces during World War II, notably in the New Guinea campaign.
- 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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8f52ca7881908704eef20228aed3 |
completed | April 14, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe8bbd051c8190a89f9801a7b08b2d |
completed | May 9, 2026, 1:19 a.m. |
Created at: April 10, 2026, 1:15 a.m.