Triple
T32548260
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gitega Airport |
E831902
|
entity |
| Predicate | politicalCapitalOfCountryServed |
P4676
|
FINISHED |
| Object | Burundi |
—
|
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: Burundi | Statement: [Gitega Airport, politicalCapitalOfCountryServed, Burundi]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalCapitalOfCountryServed Context triple: [Gitega Airport, politicalCapitalOfCountryServed, Burundi]
-
A.
governingTerritorialCapital
Indicates that a territorial entity serves as the administrative or political capital for a governing body or jurisdiction.
-
B.
capitalOfCountryServed
chosen
Indicates that a city serves as the capital of a given country.
-
C.
provinceCapitalLocatedOn
Indicates that the capital of a province is geographically situated on or alongside a specified physical feature or location (such as a river, coast, or lake).
-
D.
countryCapitalLegislatureRelation
Indicates that a specific legislature is located in, or officially associated with, the capital city of a given country.
-
E.
capitalLocation
Indicates the relationship in which a place serves as the capital city or administrative center of a given political or geographic entity.
- 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_69f34925fd08819084cfe4ec566cb704 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fde5d7d9548190880a9d95b8f0f66b |
completed | May 8, 2026, 1:32 p.m. |
| PD | Predicate disambiguation | batch_69fde4e1bf9c81909754545275eccc03 |
completed | May 8, 2026, 1:28 p.m. |
Created at: May 1, 2026, 1:02 a.m.