Triple
T23644357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brazil–Paraguay border |
E583988
|
entity |
| Predicate | adjacentToBrazilianState |
P135035
|
FINISHED |
| Object | Paraná |
—
|
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: Paraná | Statement: [Brazil–Paraguay border, adjacentToBrazilianState, Paraná]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentToBrazilianState Context triple: [Brazil–Paraguay border, adjacentToBrazilianState, Paraná]
-
A.
bordersPartOfBrazil
chosen
Indicates that one entity shares a land or maritime boundary with a specific region that lies within Brazil.
-
B.
adjacentProvince
Indicates that two provinces share a common boundary and are directly next to each other geographically.
-
C.
geographicallyAdjacentTo
Indicates that two geographic entities share a common boundary or are directly next to each other in space.
-
D.
borderingCountryOfState
Indicates that one country shares a land or maritime boundary directly with the specified state.
-
E.
hasNeighboringStateToWest
Indicates that one state is geographically located directly to the west of another state, sharing a common border.
- 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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b2832d9c8190b19c55deee39eff2 |
completed | April 29, 2026, 7:25 a.m. |
| PD | Predicate disambiguation | batch_69f118d7903c8190bb590a71771e93af |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:48 p.m.