Triple
T23996708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | San Andrés y Providencia |
E605209
|
entity |
| Predicate | geographicallyRemoteFrom |
P139716
|
FINISHED |
| Object | mainland Colombia |
—
|
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: mainland Colombia | Statement: [San Andrés y Providencia, geographicallyRemoteFrom, mainland Colombia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: geographicallyRemoteFrom Context triple: [San Andrés y Providencia, geographicallyRemoteFrom, mainland Colombia]
-
A.
geographicallySeparatedFrom
Indicates that two places or regions are distinct and apart from each other in physical location or geographic space.
-
B.
remoteness
Indicates the degree of physical or conceptual distance or isolation between entities.
-
C.
isDistant
chosen
Indicates that one entity is far away or separated by a large distance from another entity.
-
D.
distancedFrom
Indicates that one entity is physically or metaphorically kept at a certain distance or separation from another entity.
-
E.
isMoreGeographicallyDispersedThan
Indicates that one entity’s locations or presence are spread out over a wider or more scattered geographic area than another entity’s.
- 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_69e295463f7c8190b1c19dbd114641b9 |
completed | April 17, 2026, 8:17 p.m. |
| NER | Named-entity recognition | batch_69f1d38f8a208190a293c64b9c9202c0 |
completed | April 29, 2026, 9:46 a.m. |
| PD | Predicate disambiguation | batch_69f1615994c48190a5de95d3f7e5cd0a |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 9:38 p.m.