Triple
T12371442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Kameyama |
E295010
|
entity |
| Predicate | personalName |
P24312
|
FINISHED |
| Object | Tsunehito |
E1085441
|
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: Tsunehito | Statement: [Emperor Kameyama, personalName, Tsunehito]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tsunehito Context triple: [Emperor Kameyama, personalName, Tsunehito]
-
A.
Tsunehito
chosen
Tsunehito was the personal name of Emperor Kameyama, a 13th-century Japanese emperor of the Kamakura period.
-
B.
Toshimichi
Toshimichi is a Japanese given name most famously borne by Ōkubo Toshimichi, a key statesman and leader of the Meiji Restoration.
-
C.
Harukichi
Harukichi is a Japanese given name most notably borne by Harukichi Hyakutake, an Imperial Japanese Navy admiral during World War II.
-
D.
Yoshihisa
Yoshihisa is a Japanese given name commonly used for males.
-
E.
Nobuhito
Nobuhito, better known as Prince Takamatsu, was a Japanese imperial prince and the third son of Emperor Taishō, noted for his military career and postwar advocacy for peace.
- 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_69d6ab6d8a4081908636601e69ddf262 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93fa7c9ec81908c685612994543e3 |
completed | April 10, 2026, 6:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd27ee6ff881909fb0d1590580c4e8 |
completed | May 8, 2026, 12:01 a.m. |
Created at: April 8, 2026, 9:54 p.m.