Triple
T29052755
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Delo Menna |
E735304
|
entity |
| Predicate | capitalOfSubdivisionType |
P50006
|
FINISHED |
| Object | woreda |
—
|
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: woreda | Statement: [Delo Menna, capitalOfSubdivisionType, woreda]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: capitalOfSubdivisionType Context triple: [Delo Menna, capitalOfSubdivisionType, woreda]
-
A.
capitalOfSubdivision
chosen
Indicates that a place serves as the administrative capital of a specified subnational division (such as a state, province, or region).
-
B.
capitalCitySubdivisionOf
Indicates that a capital city is an administrative or territorial subdivision of a larger governing region or entity.
-
C.
countrySubdivisionCapital
Indicates that a city serves as the capital of a specific administrative subdivision (such as a state, province, or region) within a country.
-
D.
capitalOfContainingEntity
Indicates that one entity serves as the capital city or administrative center of another, larger containing entity (such as a country, state, or region).
-
E.
capitalCityOfRegion
Indicates that a city serves as the official capital of a specified region, functioning as its primary administrative or governmental center.
- 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_69f077e64b88819094d37bdbca8191b3 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f757898fe48190b124dc7301672623 |
completed | May 3, 2026, 2:11 p.m. |
| PD | Predicate disambiguation | batch_69f754c484348190948d2a04ff228fb1 |
completed | May 3, 2026, 1:59 p.m. |
Created at: April 28, 2026, 10:09 a.m.