Triple
T3845000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emperor Kanmu |
E93547
|
entity |
| Predicate | movedCapitalFrom |
P25378
|
FINISHED |
| Object | Nara |
E18488
|
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: Nara | Statement: [Emperor Kanmu, movedCapitalFrom, Nara]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nara Context triple: [Emperor Kanmu, movedCapitalFrom, Nara]
-
A.
Nara
chosen
Nara is an ancient Japanese city renowned for its early role as a national capital, its historic temples, and its culturally significant deer-filled parks.
-
B.
Nara
Nara is a Nilo-Saharan language spoken by the Nara people, an ethnic minority primarily living in western Eritrea.
-
C.
Dazaifu
Dazaifu is a historic city in Fukuoka Prefecture, Japan, known for its ancient government offices and the famous Dazaifu Tenmangū shrine dedicated to scholar-statesman Sugawara no Michizane.
-
D.
Meijō
Meijō is the Japanese name for Nagoya Castle, a historic and iconic samurai-era fortress in Nagoya, Japan.
-
E.
Kyoto
Kyoto is a historic Japanese city renowned for its well-preserved temples, traditional wooden houses, and role as the former imperial capital.
- 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_69aed96ce578819084ab16e3439976c9 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeebb655c081909ec5ff3d09eb4778 |
completed | March 9, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b56b3607948190972f83023ba04f55 |
completed | March 14, 2026, 2:05 p.m. |
Created at: March 9, 2026, 3:18 p.m.