Triple
T18289859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shirakawa-tennō |
E438082
|
entity |
| Predicate | regnalName |
P744
|
FINISHED |
| Object | Shirakawa |
—
|
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: Shirakawa | Statement: [Shirakawa-tennō, regnalName, Shirakawa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Shirakawa Context triple: [Shirakawa-tennō, regnalName, Shirakawa]
-
A.
Shirakawa
chosen
Shirakawa is the posthumous name of a Japanese emperor of the late Heian period known for consolidating cloistered rule and strengthening imperial authority.
-
B.
Shirakawa
Shirakawa is a Japanese city best known for its historic Shirakawa Castle and traditional townscape in Fukushima Prefecture.
-
C.
Shibukawa
Shibukawa is a city in Gunma Prefecture, Japan, known as a regional transport hub and gateway to nearby hot spring resorts such as Ikaho Onsen.
-
D.
Gokayama
Gokayama is a historic mountain village in Japan’s Toyama Prefecture, renowned for its traditional gassho-zukuri farmhouses and designation as a UNESCO World Heritage Site.
-
E.
Shiraoi
Shiraoi is a coastal town in Hokkaido, Japan, known for its Ainu cultural heritage and natural hot springs.
- 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_69d8b914530c8190b4474d862a2b2a1b |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e500fd65888190afdbb29dc60066af |
completed | April 19, 2026, 4:21 p.m. |
Created at: April 10, 2026, 10:35 a.m.