Triple
T30442431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tokyo (Narita) – Okinawa (Naha) |
E774485
|
entity |
| Predicate | geographicEndpointSouth |
P5249
|
FINISHED |
| Object | Ryukyu Islands |
—
|
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: Ryukyu Islands | Statement: [Tokyo (Narita) – Okinawa (Naha), geographicEndpointSouth, Ryukyu Islands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geographicEndpointSouth Context triple: [Tokyo (Narita) – Okinawa (Naha), geographicEndpointSouth, Ryukyu Islands]
-
A.
southTerminusRegion
Indicates that a given region serves as the southern endpoint or terminus of a specified route, feature, or entity.
-
B.
locatedSouthOf
Indicates that one entity is positioned geographically to the south of another entity.
-
C.
southernmost
Indicates that one entity is located farther to the south than all other comparable entities in a given set or context.
-
D.
locatedSouthWestOf
Indicates that one entity is positioned to the southwest of another entity, combining both a southern and western relative location.
-
E.
hasSouthernTerminus
chosen
Indicates that one entity serves as the southern endpoint or terminus of another entity, such as a route, line, or path.
- 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_69f22493ef9c8190ae8c2afcb7f994c8 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f71422adac8190a5ceb32dcf820833 |
completed | May 3, 2026, 9:23 a.m. |
| PD | Predicate disambiguation | batch_69f712764d2c819081b64b27e5de4a13 |
completed | May 3, 2026, 9:16 a.m. |
Created at: April 29, 2026, 8:08 p.m.