Triple
T24738431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Canton of Kourou |
E618481
|
entity |
| Predicate | lowestAdministrativeLevel |
P157070
|
FINISHED |
| Object | canton |
—
|
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: canton | Statement: [Canton of Kourou, lowestAdministrativeLevel, canton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lowestAdministrativeLevel Context triple: [Canton of Kourou, lowestAdministrativeLevel, canton]
-
A.
lowerLevelSubdivision
Indicates that one administrative or organizational unit is a smaller, subordinate subdivision within another, higher-level unit.
-
B.
highestAdministrativeLevelBelow
Indicates that one administrative unit is the most senior (top-ranked) level that is still subordinate to another specified administrative unit.
-
C.
populationLowPoint
Indicates that the population of an entity has reached its lowest recorded or observed level within a given time frame or context.
-
D.
highestLevelSubdivision
Indicates that one administrative or territorial unit is the topmost (largest or most authoritative) subdivision within a given political or geographic hierarchy.
-
E.
sharesAdministrativeLevel
Indicates that two entities are associated with the same tier or rank within an administrative or governmental hierarchy.
- F. None of above. chosen
Provenance (4 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_69e2fab8f95c81908bb9e552cf3280c2 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f410a25ab88190a72db43043c1f6ff |
completed | May 1, 2026, 2:32 a.m. |
| PD | Predicate disambiguation | batch_69f40ef612c88190ab2f3f08d4a92018 |
completed | May 1, 2026, 2:24 a.m. |
| PDg | Predicate description generation | batch_69f410a001788190a457e41f53aaf90c |
completed | May 1, 2026, 2:32 a.m. |
Created at: April 18, 2026, 4:04 a.m.