Triple
T17841804
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fujiwara no Yoshifusa |
E445546
|
entity |
| Predicate | courtTitle |
P23246
|
FINISHED |
| Object | Sadaijin |
—
|
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: Sadaijin | Statement: [Fujiwara no Yoshifusa, courtTitle, Sadaijin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sadaijin Context triple: [Fujiwara no Yoshifusa, courtTitle, Sadaijin]
-
A.
Sadaijin
chosen
Sadaijin was a high-ranking ministerial post in Japan’s imperial court, typically overseeing the left side of the government and ranking just below the chancellor in the classical ritsuryō system.
-
B.
Shobijin
Shobijin are the tiny twin priestesses who serve as Mothra’s mystical spokespeople and guardians in the Godzilla and broader kaiju film universe.
-
C.
Shoki
"Shoki" is a popular Nigerian street-hop song by Lil Kesh that helped propel him to mainstream fame and popularized a viral dance of the same name.
-
D.
Saiun
Saiun is the Allied reporting name for the Nakajima C6N, a fast and long-range Japanese carrier-based reconnaissance aircraft used during World War II.
-
E.
Akabira
Akabira is a small city in central Hokkaido, Japan, historically known as a coal-mining town.
- 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_69e48d2c3fa8819089bfbeb807a25376 |
completed | April 19, 2026, 8:07 a.m. |
Created at: April 10, 2026, 10:16 a.m.