Triple
T7509229
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sadako Kujō |
E177472
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object | Nijō Motoko |
E284133
|
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: Nijō Motoko | Statement: [Sadako Kujō, mother, Nijō Motoko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nijō Motoko Context triple: [Sadako Kujō, mother, Nijō Motoko]
-
A.
Nijō Motoko
chosen
Nijō Motoko was a Japanese noblewoman of the Nijō family and the mother of Empress Teimei, consort of Emperor Taishō.
-
B.
Yuriko
Yuriko is the given name of Japanese actress Rinko Kikuchi, known for her roles in films such as "Babel" and "Pacific Rim."
-
C.
Ikeda Riyoko
Ikeda Riyoko is a renowned Japanese manga artist best known for creating the influential historical shōjo series "The Rose of Versailles."
-
D.
Nijō Tsuruko
Nijō Tsuruko was a Japanese noblewoman of the Nijō family and the mother of Empress Shōken, consort of Emperor Meiji.
-
E.
Koizumi Kyoko
Koizumi Kyoko is a prominent Japanese singer and actress who rose to fame in the 1980s as an idol and later became acclaimed for her versatile film and television roles.
- 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_69c69f276b108190af2cc790b6554544 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f5d052888190ae8678f9134d737c |
completed | March 27, 2026, 9:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c902aadd308190bb130386af68464e |
completed | March 29, 2026, 10:44 a.m. |
Created at: March 27, 2026, 3:45 p.m.