Triple
T19220987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roraima |
E480611
|
entity |
| Predicate | largestCity |
P235
|
FINISHED |
| Object | Boa Vista |
—
|
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: Boa Vista | Statement: [Roraima, largestCity, Boa Vista]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Boa Vista Context triple: [Roraima, largestCity, Boa Vista]
-
A.
Boa Vista
Boa Vista is one of Cape Verde’s easternmost islands, known for its extensive sandy beaches, desert-like landscapes, and tourism-focused resorts.
-
B.
Boa Vista
chosen
Boa Vista is the largest city and main political and economic center of the Brazilian state of Roraima, located in the northern Amazon region near the border with Venezuela and Guyana.
-
C.
Boa Vista
Boa Vista is a central neighborhood in Recife, Brazil, known for its historic architecture, commercial activity, and cultural significance.
-
D.
São Luís Island
São Luís Island is a large Atlantic coastal island in northeastern Brazil that hosts the city of São Luís, capital of the state of Maranhão.
-
E.
São Cristóvão
São Cristóvão is one of Brazil’s oldest colonial cities, known for its well-preserved historic center and UNESCO-listed São Francisco Square.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e8cb8c348190b52075823911c869 |
completed | April 10, 2026, 12:10 p.m. |
| NER | Named-entity recognition | batch_69e5fa3fa9348190920f9d41b8beb900 |
completed | April 20, 2026, 10:04 a.m. |
Created at: April 10, 2026, 1:24 p.m.