Triple
T36068872
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kitanakagusuku |
E1043310
|
entity |
| Predicate | hasIslandSubdivision |
P174854
|
FINISHED |
| Object | Okinawa Island |
—
|
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: Okinawa Island | Statement: [Kitanakagusuku, hasIslandSubdivision, Okinawa Island]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasIslandSubdivision Context triple: [Kitanakagusuku, hasIslandSubdivision, Okinawa Island]
-
A.
hasIslandSubregion
chosen
Indicates that a region includes an island as one of its subordinate geographic subregions.
-
B.
hasSubdivision
Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
-
C.
hasIslandProvince
Indicates that a region or country possesses an administrative province that is located on an island.
-
D.
isPartOfIslandProvince
Indicates that one entity is a constituent part or region within an island province.
-
E.
hasNationalSubdivisionType
Indicates that an entity is associated with a specific type or category of national-level administrative subdivision (e.g., state, province, region).
- 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_69f76e2fd3248190b900d9a492bf5a7a |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b2c771108190adeec151daad5dab |
completed | May 3, 2026, 8:40 p.m. |
| PD | Predicate disambiguation | batch_69f7b1bad2e88190963ab4ee5d4f2038 |
completed | May 3, 2026, 8:36 p.m. |
Created at: May 3, 2026, 4:08 p.m.