Triple
T28184182
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokyo Haneda – Sapporo |
E716123
|
entity |
| Predicate | islandServedAtDestination |
P55613
|
FINISHED |
| Object | Hokkaido |
—
|
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: Hokkaido | Statement: [Tokyo Haneda – Sapporo, islandServedAtDestination, Hokkaido]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: islandServedAtDestination Context triple: [Tokyo Haneda – Sapporo, islandServedAtDestination, Hokkaido]
-
A.
islandServed
Indicates that a particular island is provided with service or coverage (such as transportation, utilities, or infrastructure) by a specified entity.
-
B.
destinationIsland
chosen
Indicates the island that serves as the endpoint or target location to which someone or something is going or being directed.
-
C.
isPortOfCallFor
Indicates that a location serves as a scheduled stop or destination for a ship, vehicle, or journey.
-
D.
servedDestination
Indicates that a service or action is directed toward, or provided to, a particular destination.
-
E.
meetsInIsland
Indicates that two or more entities meet with each other at a location that is an island.
- 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_69efd6b4fc5c81909dd88f01a8c2b35d |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69f64e37f7fc819083809149b6661e3c |
completed | May 2, 2026, 7:19 p.m. |
| PD | Predicate disambiguation | batch_69f64caede108190a35cc7cbfead866f |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 27, 2026, 10:21 p.m.