Triple
T11999009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taku City |
E285606
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Kyushu |
E13149
|
NE FINISHED |
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: Kyushu | Statement: [Taku City, locatedIn, Kyushu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kyushu Context triple: [Taku City, locatedIn, Kyushu]
-
A.
Kyushu
chosen
Kyushu is the southwesternmost of Japan’s main islands, known for its active volcanoes, hot springs, and historic cities such as Fukuoka and Nagasaki.
-
B.
Kyushu (Ryukyu Islands)
Kyushu (Ryukyu Islands) is a southwestern Japanese region encompassing the main island of Kyushu and the Ryukyu archipelago, known for its subtropical climate, active volcanoes, and distinct Ryukyuan cultural heritage.
-
C.
Shikoku
Shikoku is the smallest of Japan’s four main islands, known for its mountainous landscapes, traditional rural culture, and the famous 88-temple Buddhist pilgrimage route.
-
D.
Honshu
Honshu is the largest and most populous island of Japan, home to major cities such as Tokyo, Osaka, and Kyoto.
-
E.
Yamato region
The Yamato region is the early political and cultural heartland of Japan, where the first unified Japanese state emerged under the Yamato court.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c26d7881909b67a31d04882eb5 |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63ed82a548190ab9326daef78e30b |
completed | May 2, 2026, 6:13 p.m. |
Created at: April 8, 2026, 9:46 p.m.