Triple
T22818894
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CP Air |
E565174
|
entity |
| Predicate | notableRoute |
P22
|
FINISHED |
| Object |
Vancouver–Tokyo
Vancouver–Tokyo was a prominent international route connecting Canada and Japan that helped establish CP Air’s presence in trans-Pacific aviation.
|
E1556115
|
NE FINISHED |
How this triple was built (4 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: Vancouver–Tokyo | Statement: [CP Air, notableRoute, Vancouver–Tokyo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vancouver–Tokyo Context triple: [CP Air, notableRoute, Vancouver–Tokyo]
-
A.
London–Tokyo
London–Tokyo is a major intercontinental air route linking the capital cities of the United Kingdom and Japan.
-
B.
Seoul–Tokyo
Seoul–Tokyo is a major international air route connecting the capitals of South Korea and Japan, serving as a key corridor for business and tourism between the two countries.
-
C.
Moscow–Tokyo
Moscow–Tokyo refers to the long-haul international air route connecting the capitals of Russia and Japan.
-
D.
Kobe – Sapporo
Kobe – Sapporo is a domestic air route in Japan connecting the city of Kobe in Hyōgo Prefecture with Sapporo on the northern island of Hokkaido.
-
E.
Vancouver
Vancouver is an Australian-bred Thoroughbred racehorse best known for winning the 2015 Golden Slipper Stakes and later standing as a successful sire.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Vancouver–Tokyo Triple: [CP Air, notableRoute, Vancouver–Tokyo]
Generated description
Vancouver–Tokyo was a prominent international route connecting Canada and Japan that helped establish CP Air’s presence in trans-Pacific aviation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vancouver–Tokyo Target entity description: Vancouver–Tokyo was a prominent international route connecting Canada and Japan that helped establish CP Air’s presence in trans-Pacific aviation.
-
A.
London–Tokyo
London–Tokyo is a major intercontinental air route linking the capital cities of the United Kingdom and Japan.
-
B.
Seoul–Tokyo
Seoul–Tokyo is a major international air route connecting the capitals of South Korea and Japan, serving as a key corridor for business and tourism between the two countries.
-
C.
Moscow–Tokyo
Moscow–Tokyo refers to the long-haul international air route connecting the capitals of Russia and Japan.
-
D.
Kobe – Sapporo
Kobe – Sapporo is a domestic air route in Japan connecting the city of Kobe in Hyōgo Prefecture with Sapporo on the northern island of Hokkaido.
-
E.
Vancouver
Vancouver is an Australian-bred Thoroughbred racehorse best known for winning the 2015 Golden Slipper Stakes and later standing as a successful sire.
- F. None of above. chosen
Provenance (5 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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17dce762c8190934fb921f942c9fd |
completed | April 29, 2026, 3:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b9ea6b87c819088abf95f56014724 |
completed | May 18, 2026, 11:20 p.m. |
| NEDg | Description generation | batch_6a0ba271f1548190afa04f8cf4d1da0b |
completed | May 18, 2026, 11:36 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0ba3b3cb288190a96a23d310c16d52 |
completed | May 18, 2026, 11:41 p.m. |
Created at: April 17, 2026, 3:33 p.m.