Triple
T14199882
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mafra, Santa Catarina, Brazil |
E351934
|
entity |
| Predicate | roadConnection |
P385
|
FINISHED |
| Object | BR-116 |
E768481
|
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: BR-116 | Statement: [Mafra, Santa Catarina, Brazil, roadConnection, BR-116]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BR-116 Context triple: [Mafra, Santa Catarina, Brazil, roadConnection, BR-116]
-
A.
BR-110
BR-110 is a federal highway in Brazil that connects the city of Mossoró to other regions in the country’s Northeast.
-
B.
BR-101
BR-101 is one of Brazil’s longest and most important federal highways, running along much of the country’s Atlantic coast and linking numerous major cities and states.
-
C.
BR-116 highway
chosen
BR-116 highway is one of Brazil's longest and most important federal highways, running north–south and connecting major cities across the country.
-
D.
BR-10
BR-10 is the vehicle registration code assigned to the Bhagalpur district in the Indian state of Bihar.
-
E.
BR-163 highway
BR-163 highway is a major Brazilian federal road that runs through the Amazon region, linking the interior agricultural areas to key river ports and export routes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d827894ac0819097803e57f3227b23 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de61f472548190a1a7edc40526eac3 |
completed | April 14, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd194f13688190af7ef5ceb92a73ff |
completed | May 7, 2026, 10:59 p.m. |
Created at: April 10, 2026, 1:04 a.m.