Triple
T9044945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ISO 3166-2:GE |
E216731
|
entity |
| Predicate | subdivisionCodeExample |
P22016
|
FINISHED |
| Object | GE-AB |
—
|
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: GE-AB | Statement: [ISO 3166-2:GE, subdivisionCodeExample, GE-AB]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: subdivisionCodeExample Context triple: [ISO 3166-2:GE, subdivisionCodeExample, GE-AB]
-
A.
hasSubdivisionExample
Indicates that one entity is an example or instance of a subdivision or component part of another entity.
-
B.
hasSubdivisionCode
chosen
Indicates that an entity is associated with a specific code identifying one of its internal subdivisions (such as a state, province, or region).
-
C.
hasSubdivisionCodePart
Indicates that an entity’s subdivision code includes or is composed of the referenced code segment or component.
-
D.
subdivisionOfJurisdiction
Indicates that one jurisdiction is a smaller administrative or territorial unit that forms part of a larger jurisdiction.
-
E.
hasSubdivisionCodeContext
Indicates that a subdivision code is interpreted within a specific coding or contextual framework that defines its meaning.
- 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b148b188190814d64acae493634 |
completed | April 1, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69cc5ee566b081909e3cdaf551dbd0ec |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:09 p.m.