Triple
T24261424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | canton of Decazeville |
E604712
|
entity |
| Predicate | hasBorderingUnitType |
P64694
|
FINISHED |
| Object | other cantons of Aveyron department |
—
|
LITERAL 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: other cantons of Aveyron department | Statement: [canton of Decazeville, hasBorderingUnitType, other cantons of Aveyron department]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBorderingUnitType Context triple: [canton of Decazeville, hasBorderingUnitType, other cantons of Aveyron department]
-
A.
borderingUnitType
chosen
Indicates that one unit is adjacent to another unit of a specified type along a shared boundary.
-
B.
hasNeighbouringUnit
Indicates that one unit is directly adjacent to and shares a boundary or side with another unit.
-
C.
hasBorderConflictWith
Indicates a relationship where two entities share a disputed boundary or are involved in an ongoing or historical conflict over their common border.
-
D.
hasBoundaryUnit
Indicates that one entity uses or is associated with a specific unit of measurement for its boundary or limit.
-
E.
hasBorderConnection
Indicates that two regions or entities share a common boundary or are directly connected along a 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_69e29544c29c8190b023606eafe5d36a |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f28c6727388190862e3ce09c372c70 |
completed | April 29, 2026, 10:55 p.m. |
| PD | Predicate disambiguation | batch_69f1c450aa508190bc9d372a5f6ee47a |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 18, 2026, 12:06 a.m.