Triple
T20515136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ryūjin |
E503665
|
entity |
| Predicate | child |
P120
|
FINISHED |
| Object | Toyotama-hime |
—
|
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: Toyotama-hime | Statement: [Ryūjin, child, Toyotama-hime]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toyotama-hime Context triple: [Ryūjin, child, Toyotama-hime]
-
A.
Toyotama-hime
chosen
Toyotama-hime is a dragon princess and sea deity in Japanese mythology, known as the wife of Hoori and mother of the legendary first human emperor’s ancestor.
-
B.
Tamayori-hime
Tamayori-hime is a goddess in Japanese mythology, often associated with water and the sea, revered as the mother of Japan’s legendary first emperor, Emperor Jimmu.
-
C.
Hidaka-hime
Hidaka-hime is the birth name of Empress Genshō, a Nara-period Japanese empress who ruled in the early 8th century.
-
D.
Asahi-hime
Asahi-hime was a Japanese noblewoman of the late Sengoku period, known for her politically significant marriage into the Tokugawa clan that helped secure alliances during Japan’s unification.
-
E.
Yakami-hime
Yakami-hime is a goddess in Japanese mythology known as a consort of the deity Ōkuninushi and as a figure in the Izumo cycle of legends.
- 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_69e0b4b2aa788190ae9eb37c1d73b1f1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69f4133048190abb777be4b65c2c4 |
completed | April 20, 2026, 9:48 p.m. |
Created at: April 16, 2026, 11:36 a.m.