Triple
T30332674
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chishima Islands of Hokkaido Prefecture |
E771526
|
entity |
| Predicate | geographicalDirectionFromHokkaido |
P178327
|
FINISHED |
| Object | northeast |
—
|
LITERAL 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: northeast | Statement: [Chishima Islands of Hokkaido Prefecture, geographicalDirectionFromHokkaido, northeast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geographicalDirectionFromHokkaido Context triple: [Chishima Islands of Hokkaido Prefecture, geographicalDirectionFromHokkaido, northeast]
-
A.
locatedInDirectionFromTokyo
Indicates that one place is situated in a specified compass direction relative to Tokyo.
-
B.
offshoreDistanceFromHokkaido_km
Indicates the distance, in kilometers, that something is located offshore from the coast of Hokkaido.
-
C.
regionOfJapan
Indicates that one entity is a geographic region that is part of, or located within, Japan.
-
D.
adjacentStationOnHakodateMainLine
Indicates that one station is directly next to another station along the Hakodate Main Line, with no other stations in between.
-
E.
positionOnHonshu
Indicates that one entity is geographically located on the island of Honshu in Japan.
- F. None of above. chosen
Provenance (4 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_69f2248aba24819095bb86480d55b23b |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f70e8755a48190931eaa77946f9460 |
completed | May 3, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f70abc00848190a1c3f495ef6c8dc6 |
completed | May 3, 2026, 8:43 a.m. |
| PDg | Predicate description generation | batch_69f70e854b9c8190a3416e2189e17742 |
completed | May 3, 2026, 8:59 a.m. |
Created at: April 29, 2026, 7:53 p.m.