Triple
T37246055
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kouilou region |
E923854
|
entity |
| Predicate | countryCapitalLocatedElsewhere |
P169938
|
FINISHED |
| Object | Brazzaville |
E14466
|
NE 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: Brazzaville | Statement: [Kouilou region, countryCapitalLocatedElsewhere, Brazzaville]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryCapitalLocatedElsewhere Context triple: [Kouilou region, countryCapitalLocatedElsewhere, Brazzaville]
-
A.
countryCapitalLocatedOn
Indicates that the capital city of a country is situated on or directly adjacent to a specified geographic feature (such as a river, coast, or lake).
-
B.
countryCapitalLocatedWithin
Indicates that the capital city of a country is geographically situated within the boundaries of that country.
-
C.
countryCapitalOverlooked
Indicates that a country's capital city is being neglected, ignored, or insufficiently recognized in a given context or consideration.
-
D.
capitalOfGoverningCountry
chosen
Indicates that a city serves as the capital of the country that governs a given territory or region.
-
E.
hasCountryOfCapital
Indicates that a capital city is associated with or belongs to a specific country.
- F. None of above.
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_69f76eaabb4c819093b751b139dad551 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a035052a47081908e9e56e21c543d46 |
completed | May 12, 2026, 4:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4076e7cabc81908f83750d8bda3e13 |
completed | June 28, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_6a034d306e588190a2dce906fd46eb54 |
completed | May 12, 2026, 3:54 p.m. |
Created at: May 3, 2026, 4:15 p.m.