Triple
T21685005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 長門国豊浦郡下関 |
E535206
|
entity |
| Predicate | 別名 |
P39
|
FINISHED |
| Object | 馬関 |
—
|
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: 馬関 | Statement: [長門国豊浦郡下関, 別名, 馬関]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 馬関 Context triple: [長門国豊浦郡下関, 別名, 馬関]
-
A.
Shimonoseki
chosen
Shimonoseki is a Japanese port city at the southwestern tip of Honshu known as a key maritime gateway between Japan and the Korean Peninsula.
-
B.
Isehara
Isehara is a city in Kanagawa Prefecture, Japan, known as a residential and industrial area with access to nearby natural attractions such as the Tanzawa Mountains.
-
C.
Ushijima
Ushijima is a Japanese surname borne by various notable individuals, including military figures and fictional characters.
-
D.
Nakanoshima
Nakanoshima is a small Japanese island associated with Etajima in Hiroshima Prefecture, known for its coastal scenery and role within the local island group.
-
E.
Nakanoshima
Nakanoshima is a central river island and business district in Osaka, Japan, known for its government buildings, cultural institutions, and scenic waterfront parks.
- 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_69e0c469b6ec8190aee4cadd1527db91 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef96ca668481909f53853c7a8ea811 |
completed | April 27, 2026, 5:03 p.m. |
Created at: April 16, 2026, 6:44 p.m.