Triple
T679481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kyushu |
E13149
|
entity |
| Predicate | positionRelativeToJapan |
P5132
|
FINISHED |
| Object | southwesternmost main island |
—
|
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: southwesternmost main island | Statement: [Kyushu, positionRelativeToJapan, southwesternmost main island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: positionRelativeToJapan Context triple: [Kyushu, positionRelativeToJapan, southwesternmost main island]
-
A.
positionRelativeToCoast
Indicates the spatial relationship of something to a coastline, such as its distance or orientation relative to the coast.
-
B.
ianaLocation
Indicates that an entity is associated with a specific geographic or network location identified using an IANA-defined naming or coding scheme.
-
C.
refersToLocation
Indicates that one entity designates, points to, or identifies a specific location associated with it.
-
D.
positionB
chosen
Indicates that one entity occupies or is located at a specific position relative to another entity.
-
E.
deltaLocation
Indicates a change or difference between two locations, typically specifying how one location has shifted relative to another.
- 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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a04f4efc819082767a7517fa760a |
completed | March 1, 2026, 8:23 p.m. |
| PD | Predicate disambiguation | batch_69a49d1d79608190a849ba9ffad2879d |
completed | March 1, 2026, 8:10 p.m. |
Created at: March 1, 2026, 7:36 p.m.