Triple
T19289613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prince Naruhiko Higashikuni |
E482405
|
entity |
| Predicate | nativeName |
P15
|
FINISHED |
| Object | 東久邇宮稔彦王 |
—
|
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: 東久邇宮稔彦王 | Statement: [Prince Naruhiko Higashikuni, nativeName, 東久邇宮稔彦王]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 東久邇宮稔彦王 Context triple: [Prince Naruhiko Higashikuni, nativeName, 東久邇宮稔彦王]
-
A.
東久邇宮稔彦王
chosen
東久邇宮稔彦王 was a Japanese imperial prince and military officer who briefly served as prime minister of Japan in the immediate aftermath of World War II.
-
B.
三笠宮崇仁親王
三笠宮崇仁親王は、大正天皇の第四皇子であり、昭和から平成にかけて長く存命した日本の皇族で、歴史学者としても知られた人物である。
-
C.
秋篠宮
秋篠宮は、日本の皇室に属する皇嗣であり、天皇徳仁の弟にあたる皇族男性である。
-
D.
久邇宮邦彦王
久邇宮邦彦王 was a Japanese imperial prince of the Kuni-no-miya house who served as a senior military officer and played a prominent role in the politics and aristocracy of the late Meiji and Taishō periods.
-
E.
Prince Nobuhito of Takamatsu
Prince Nobuhito of Takamatsu was a Japanese imperial prince, naval officer, and younger brother of Emperor Shōwa who played a notable role in Japan’s early Shōwa-era history.
- 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_69d8e8cf61b0819096fe3e4107827c4e |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fc050a888190ac204d1e736200c5 |
completed | April 20, 2026, 10:12 a.m. |
Created at: April 10, 2026, 1:30 p.m.