Triple
T12675751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portopia Island |
E302806
|
entity |
| Predicate | connectedTo |
P37
|
FINISHED |
| Object | mainland Kobe |
E448253
|
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: mainland Kobe | Statement: [Portopia Island, connectedTo, mainland Kobe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: mainland Kobe Context triple: [Portopia Island, connectedTo, mainland Kobe]
-
A.
Nada-ku, Kobe
Nada-ku, Kobe is a ward of Kobe, Japan, known for its scenic Mount Rokko area, sake breweries, and residential neighborhoods.
-
B.
Kobe Nankinmachi
Kobe Nankinmachi is a famous Chinatown district in Kobe, Japan, known for its Chinese restaurants, shops, and vibrant cultural festivals.
-
C.
Higashinada-ku, Kobe
chosen
Higashinada-ku, Kobe is a coastal ward in eastern Kobe, Japan, known for its residential districts, sake breweries, and man-made islands such as Rokkō Island.
-
D.
Hyogo-ku, Kobe
Hyogo-ku, Kobe is one of the central wards of Kobe, Japan, known for its mix of residential districts, historic sites, and industrial waterfront areas.
-
E.
Nagata-ku, Kobe
Nagata-ku, Kobe is one of the wards of Kobe, Japan, known as a traditional working-class and industrial area with a significant history, including heavy damage in the 1995 Great Hanshin earthquake.
- 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_69d7bdee64a08190801c6d470aefd723 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961b0d9c88190a05d6cbcb7a1642d |
completed | April 10, 2026, 8:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f671a163188190b6077c77f9a81681 |
completed | May 2, 2026, 9:50 p.m. |
Created at: April 9, 2026, 5:20 p.m.