Triple
T6089156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KGR |
E135716
|
entity |
| Predicate | regionCodeLevel |
P68047
|
FINISHED |
| Object | subnational |
—
|
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: subnational | Statement: [KGR, regionCodeLevel, subnational]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regionCodeLevel Context triple: [KGR, regionCodeLevel, subnational]
-
A.
regionCodeType
Indicates the classification or format type used for a given region code within a coding or identification system.
-
B.
regionNumber
Indicates that an entity is assigned to or associated with a specific numbered region within a larger spatial or organizational division.
-
C.
districtCode
Indicates that an entity is associated with, or identified by, a specific administrative district code.
-
D.
regionCodeSystem
Indicates that a region is identified or classified according to a particular coding system for geographic or administrative areas.
-
E.
associatedCountrySubdivisionCode
Indicates the specific administrative region or subdivision code within a country that is linked to or relevant for the given entity.
- 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_69c0087bcc788190b20f093d3a6c60ec |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c057a862c88190912a913973c6b6fc |
completed | March 22, 2026, 8:57 p.m. |
| PD | Predicate disambiguation | batch_69c049f3b1ec8190bea67a7bec6442a5 |
completed | March 22, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69c04e8e3f2c8190be459ca02f9b315a |
completed | March 22, 2026, 8:18 p.m. |
Created at: March 22, 2026, 4:12 p.m.