Triple
T15855523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ōtsu |
E384443
|
entity |
| Predicate | hasPort |
P35
|
FINISHED |
| Object | Port of Ōtsu |
E648315
|
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: Port of Ōtsu | Statement: [Ōtsu, hasPort, Port of Ōtsu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Port of Ōtsu Context triple: [Ōtsu, hasPort, Port of Ōtsu]
-
A.
Port of Otsu
chosen
Port of Otsu is a lakeside harbor and passenger terminal on Lake Biwa in Ōtsu, Japan, serving as a hub for sightseeing cruises and regional water transport.
-
B.
Port of Kuwana
The Port of Kuwana is a Japanese maritime hub located in Mie Prefecture, serving as a regional gateway for shipping and coastal trade along Ise Bay.
-
C.
Port of Sakaide
The Port of Sakaide is a Japanese seaport in Kagawa Prefecture on Shikoku, serving as an important industrial and logistics hub near the Seto Ohashi Bridge.
-
D.
Kishiwada Port
Kishiwada Port is a coastal harbor facility in Kishiwada, Osaka Prefecture, Japan, serving regional maritime transport and local industry.
-
E.
Port of Shimizu
The Port of Shimizu is a major Japanese seaport in Shizuoka Prefecture, known for its scenic views of Mount Fuji and its role in regional trade and industry.
- 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_69d86da422088190aac39e32e6c68429 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e14caf6ae481909ae1385cb4548612 |
completed | April 16, 2026, 8:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa14977408190815ef02cc54075cc |
completed | May 9, 2026, 9:04 p.m. |
Created at: April 10, 2026, 4:50 a.m.