Triple
T8436372
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bahia |
E199233
|
entity |
| Predicate | borders |
P224
|
FINISHED |
| Object | Piauí |
E149952
|
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: Piauí | Statement: [Bahia, borders, Piauí]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Piauí Context triple: [Bahia, borders, Piauí]
-
A.
Piauí
chosen
Piauí is a state in northeastern Brazil known for its semi-arid landscapes, short Atlantic coastline, and rich archaeological sites such as those in Serra da Capivara National Park.
-
B.
Ceará
Ceará is a state in northeastern Brazil known for its long Atlantic coastline, semi-arid interior, and vibrant cultural traditions centered around its capital, Fortaleza.
-
C.
Sergipe
Sergipe is a small coastal state in northeastern Brazil known for its Atlantic shoreline, colonial history, and role in the broader Dutch and Portuguese colonial era.
-
D.
Maranhão
Maranhão is a northeastern Brazilian state known for its colonial heritage, Afro-Brazilian culture, and the Lençóis Maranhenses dune and lagoon landscapes.
-
E.
Pernambuco
Pernambuco is a northeastern Brazilian state known for its historic capital Recife, rich colonial and Afro-Brazilian cultural heritage, and significant role in Brazil’s sugarcane economy.
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe132a6f881908f990089792fccc4 |
completed | March 31, 2026, 2:58 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d12cabbb088190bada143db831c466 |
completed | April 4, 2026, 3:22 p.m. |
Created at: March 30, 2026, 6:08 p.m.