Triple
T14132137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanmon Tunnel |
E350194
|
entity |
| Predicate | connects |
P390
|
FINISHED |
| Object | Moji-ku |
—
|
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: Moji-ku | Statement: [Kanmon Tunnel, connects, Moji-ku]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Moji-ku Context triple: [Kanmon Tunnel, connects, Moji-ku]
-
A.
Moji-ku
chosen
Moji-ku is a historic ward of Kitakyushu, Japan, known for its preserved port town atmosphere and Meiji-era architecture around Mojiko Retro District.
-
B.
Suminoe-ku
Suminoe-ku is one of the 24 wards of Osaka, Japan, known for its coastal location, port facilities, and large-scale residential and commercial developments.
-
C.
Sumiyoshi-ku
Sumiyoshi-ku is one of the 24 wards of Osaka, Japan, known as a primarily residential area with a mix of traditional neighborhoods and urban amenities.
-
D.
Minuma-ku
Minuma-ku is one of the administrative wards of Saitama City in Saitama Prefecture, Japan, known for its mix of residential areas and green spaces.
-
E.
Miyagino-ku
Miyagino-ku is one of the administrative wards of Sendai, Japan, known for its mix of residential areas, commercial facilities, and transportation hubs.
- 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_69d827865f608190b311820428ae027b |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de610cece88190b4a86500677e5938 |
completed | April 14, 2026, 3:45 p.m. |
Created at: April 9, 2026, 11:24 p.m.