Triple
T19417179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kuni no miya Kunihito |
E485751
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Kuni |
—
|
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: Kuni | Statement: [Kuni no miya Kunihito, familyName, Kuni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kuni Context triple: [Kuni no miya Kunihito, familyName, Kuni]
-
A.
Kuni
chosen
Kuni is the Japanese noble family name of Empress Kōjun, consort of Emperor Shōwa (Hirohito) and mother of Emperor Emeritus Akihito.
-
B.
Kunri
Kunri is a town in Pakistan’s Sindh province known as a major center for red chili production and trade.
-
C.
Kunis
Kunis is the surname of actress Mila Kunis, a Ukrainian-born American performer known for roles in "That '70s Show," "Black Swan," and as the voice of Meg Griffin on "Family Guy."
-
D.
Kōjun
Kōjun was the posthumous name of Empress Kōjun, the wife of Emperor Shōwa (Hirohito) and mother of Emperor Emeritus Akihito of Japan.
-
E.
Konomihu
Konomihu is an extinct Native American language variety traditionally spoken in northern California, considered a dialect of the Shasta language.
- 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_69d8e8d688f881909c85104a62e09d8a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62afad8d881908f1de6324e55d2f6 |
completed | April 20, 2026, 1:32 p.m. |
Created at: April 10, 2026, 1:37 p.m.