Triple
T33014866
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bundung |
E844746
|
entity |
| Predicate | belongsToCountryCapitalRegion |
P146630
|
FINISHED |
| Object | Greater Banjul Area |
—
|
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: Greater Banjul Area | Statement: [Bundung, belongsToCountryCapitalRegion, Greater Banjul Area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: belongsToCountryCapitalRegion Context triple: [Bundung, belongsToCountryCapitalRegion, Greater Banjul Area]
-
A.
hasCapitalRegionRelation
Indicates a relationship where one entity serves as the capital region or administrative capital area of another entity.
-
B.
majorCountryCapitalRegion
Indicates that a region serves as the capital area or primary administrative region of a major country.
-
C.
belongsToNationCapitalArea
chosen
Indicates that something is part of, or located within, the capital-area region of a specified nation.
-
D.
connectsCapitalWithRegion
Indicates a relationship where a capital city is linked or associated with the larger region it belongs to.
-
E.
countryCapitalRegion
Indicates that a specified region is the capital region (administrative capital area) of a given country.
- 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_69f3494f3b4081909dccf2af34372a26 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ff0214d7348190904688376df99bce |
completed | May 9, 2026, 9:44 a.m. |
| PD | Predicate disambiguation | batch_69feffd62fec8190a855922c8b3c57cf |
completed | May 9, 2026, 9:35 a.m. |
Created at: May 1, 2026, 1:23 a.m.