Triple
T23996665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bajo Nuevo Reef |
E605207
|
entity |
| Predicate | nearestInhabitedArea |
P21721
|
FINISHED |
| Object | San Andrés Island (Colombia) |
—
|
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: San Andrés Island (Colombia) | Statement: [Bajo Nuevo Reef, nearestInhabitedArea, San Andrés Island (Colombia)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearestInhabitedArea Context triple: [Bajo Nuevo Reef, nearestInhabitedArea, San Andrés Island (Colombia)]
-
A.
nearestInhabitedTerritory
chosen
Indicates that one territory is the closest inhabited territory to another specified location or territory.
-
B.
nearestArea
Indicates that one area is the closest in distance to a given reference point or region compared to all other candidate areas.
-
C.
nearbySettlementRegion
Indicates that a settlement is located close to or within the surrounding area of a specified region.
-
D.
hasNearestLargerSettlement
Indicates that one settlement is associated with the geographically closest settlement that is larger in size or population.
-
E.
nearestTownCenter
Indicates that one location is the closest town center to another specified point or area.
- 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.