Triple
T17836971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujiwara no Kamatari |
E445414
|
entity |
| Predicate | posthumousTitle |
P4225
|
FINISHED |
| Object | Taishōkan |
—
|
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: Taishōkan | Statement: [Fujiwara no Kamatari, posthumousTitle, Taishōkan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taishōkan Context triple: [Fujiwara no Kamatari, posthumousTitle, Taishōkan]
-
A.
Taishōkan
chosen
Taishōkan is an honorific title historically associated with the eminent Japanese statesman Fujiwara no Kamatari, founder of the influential Fujiwara clan.
-
B.
Keihō
Keihō is the primary criminal law code of Japan that defines offenses and their penalties.
-
C.
Daijō
Daijō is a Japanese term historically associated with imperial titles and court ranks, particularly in reference to retired emperors.
-
D.
Genshō
Genshō was an 8th-century Japanese empress who ruled during the Nara period and is known for continuing the centralizing reforms of her predecessors.
-
E.
Enyō
Enyō is a minor Greek goddess associated with war, destruction, and the bloody chaos of battle, often depicted as a companion of Ares.
- 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48d28c14881909033abd09bbdb135 |
completed | April 19, 2026, 8:07 a.m. |
Created at: April 10, 2026, 10:16 a.m.