Triple
T23376374
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 神宮 |
E593615
|
entity |
| Predicate | hasReading |
P55333
|
FINISHED |
| Object | じんぐう (jingū) |
—
|
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: じんぐう (jingū) | Statement: [神宮, hasReading, じんぐう (jingū)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: じんぐう (jingū) Context triple: [神宮, hasReading, じんぐう (jingū)]
-
A.
jingū
chosen
A jingū is a major Shinto shrine of particularly high status, often associated with the imperial family or significant national deities in Japan.
-
B.
Jingū
Jingū is the formal name for the Ise Grand Shrine, Japan’s most sacred Shinto shrine dedicated primarily to the sun goddess Amaterasu.
-
C.
Jinjur
Jinjur is a fictional character from L. Frank Baum’s Oz series, known as the ambitious young leader of a revolt against the Emerald City’s rulers.
-
D.
Genkū
Genkū is the religious name of Hōnen, the influential Japanese Buddhist priest who founded the Jōdo-shū (Pure Land) school in the late 12th century.
-
E.
Jinguashi
Jinguashi is a historic former gold and copper mining town in New Taipei, Taiwan, known for its mountainous scenery, Japanese-era relics, and heritage sites like the Gold Ecological Park.
- 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_69e25d268a50819095f2fd479da8ef3f |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1a3b3cc348190953d0b0ebac9c5dd |
completed | April 29, 2026, 6:22 a.m. |
Created at: April 17, 2026, 5:33 p.m.