Triple
T19734199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hayama Shiosai Park |
E473932
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Kamakura |
—
|
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: Kamakura | Statement: [Hayama Shiosai Park, near, Kamakura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kamakura Context triple: [Hayama Shiosai Park, near, Kamakura]
-
A.
Kamakura
chosen
Kamakura is a historic coastal city in Japan renowned for its Great Buddha statue, numerous temples and shrines, and role as the political center of the Kamakura shogunate.
-
B.
Minamoto-shi
Minamoto-shi is the romanized Japanese term for the Minamoto clan, a powerful and historically significant samurai family that played a central role in early Japanese politics and warfare.
-
C.
Ashikaga
Ashikaga was a powerful samurai clan that ruled Japan as shoguns during the Muromachi period (1336–1573).
-
D.
Ashikaga
Ashikaga is a historic city in Japan known for its cultural heritage sites, including Ashikaga Gakko (one of Japan’s oldest schools) and the popular Ashikaga Flower Park.
-
E.
Sanjō
Sanjō was a Japanese emperor of the Heian period, remembered for his brief reign and subsequent abdication due to failing eyesight.
- 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_69d8e517ebd48190979ee76723bcfadf |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6515b4d308190af3be1787fa7c65b |
completed | April 20, 2026, 4:16 p.m. |
Created at: April 10, 2026, 1:47 p.m.