Triple
T10447466
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 大平正芳 |
E246329
|
entity |
| Predicate | ローマ字表記 |
P2508
|
FINISHED |
| Object | Masayoshi Ohira |
E48180
|
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: Masayoshi Ohira | Statement: [大平正芳, ローマ字表記, Masayoshi Ohira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Masayoshi Ohira Context triple: [大平正芳, ローマ字表記, Masayoshi Ohira]
-
A.
Masayoshi Ōhira
chosen
Masayoshi Ōhira was a Japanese politician who served as Prime Minister of Japan from 1978 until his death in 1980.
-
B.
Hiroshi Sakurazaka
Hiroshi Sakurazaka is a Japanese science fiction author best known internationally for his novel "All You Need Is Kill," which inspired the film "Edge of Tomorrow."
-
C.
Masi Oka
Masi Oka is a Japanese-American actor and digital effects artist best known for his role as Hiro Nakamura on the television series "Heroes."
-
D.
Eiichi Kono
Eiichi Kono is a Japanese type designer best known for his work on the digital revival and refinement of the iconic Johnston typeface used across the London Underground.
-
E.
Takeshi Ando
Takeshi Ando is a Japanese sculptor best known for creating the current bronze statue of the loyal dog Hachiko in Tokyo.
- 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_69d381c04fe08190957c26c526a3b05a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4fdc10c8081908a3801fe1dea63de |
completed | April 7, 2026, 12:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcdee6798c8190b2b47082cf0c32fb |
completed | May 7, 2026, 6:50 p.m. |
Created at: April 6, 2026, 12:16 p.m.