Triple
T14284830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 港区 |
E354141
|
entity |
| Predicate | hasBusinessDistrict |
P459
|
FINISHED |
| Object | 新橋 |
E1090672
|
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: 新橋 | Statement: [港区, hasBusinessDistrict, 新橋]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 新橋 Context triple: [港区, hasBusinessDistrict, 新橋]
-
A.
新橋
chosen
新橋 is a bustling business and entertainment district in central Tokyo known for its salaryman culture, izakaya alleys, and major railway hub.
-
B.
五条大橋
五条大橋 is a historic bridge in Kyoto, Japan, best known as the legendary site of the encounter between the warrior monk Benkei and the folk hero Minamoto no Yoshitsune.
-
C.
Nijūbashi Bridge
Nijūbashi Bridge is a famous pair of arched bridges at the main entrance to Tokyo’s Imperial Palace, known as one of Japan’s most iconic and photographed landmarks.
-
D.
Shijō Bridge
Shijō Bridge is a historic and bustling bridge in central Kyoto, Japan, linking the Gion district with downtown shopping and entertainment areas across the Kamo River.
-
E.
朝潮橋駅
朝潮橋駅は、大阪市港区に位置し、大阪メトロ中央線が乗り入れる都市型の地下鉄駅です。
- 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_69d8278d25148190abf1a8c8f5f533ad |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de697ef40c8190bea37724b28c2e99 |
completed | April 14, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd467f3b3081908261261301674c4e |
completed | May 8, 2026, 2:12 a.m. |
Created at: April 10, 2026, 1:10 a.m.