Triple
T27524025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japan–South Korea |
E694786
|
entity |
| Predicate | hasAirRoute |
P105188
|
FINISHED |
| Object | Tokyo–Seoul |
—
|
NE NERFINISHED |
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: Tokyo–Seoul | Statement: [Japan–South Korea, hasAirRoute, Tokyo–Seoul]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasAirRoute Context triple: [Japan–South Korea, hasAirRoute, Tokyo–Seoul]
-
A.
hasAirTravelLink
chosen
Indicates that there is a direct or established air travel connection (such as flights or air routes) between the related entities.
-
B.
hasAirlines
Indicates that one entity (such as an airport, city, or country) is served by or associated with one or more airline operators.
-
C.
hasAirportAccessTo
Indicates that one location or entity has direct access to another via an airport connection or service.
-
D.
hasCityPair
Indicates a relationship that links two cities considered as a connected or associated pair, often for purposes such as travel, trade, or comparison.
-
E.
airlineServiceVia
Indicates that an airline service operates between two locations with a specified intermediate stop or transit point.
- F. None of above.
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_69ef538550208190aa9de8e2cb260d93 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62f2e2df88190948551f6fd67a65a |
completed | May 2, 2026, 5:06 p.m. |
| PD | Predicate disambiguation | batch_69f623ac3a9c8190a6ee0c137b09e4b0 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 1:22 p.m.