Triple
T7654514
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cayo Aurora |
E173343
|
entity |
| Predicate | hasApproximateDistanceFromShore |
P15760
|
FINISHED |
| Object | about 1 mile from mainland Guánica |
—
|
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: about 1 mile from mainland Guánica | Statement: [Cayo Aurora, hasApproximateDistanceFromShore, about 1 mile from mainland Guánica]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateDistanceFromShore Context triple: [Cayo Aurora, hasApproximateDistanceFromShore, about 1 mile from mainland Guánica]
-
A.
stateOnNearestShore
Indicates that an entity is located on the shore that is geographically closest to another specified reference point or entity.
-
B.
distanceFromCoast
chosen
Indicates the measured spatial separation between a location and the nearest point on a coastline.
-
C.
hasNearbyCoast
Indicates that one location is situated close to a coastline or seashore.
-
D.
visibilityFromShore
Indicates that something can be seen or is visually detectable from the shoreline or coast.
-
E.
nearIsland
Indicates that one entity is located close to or in the vicinity of an island.
- 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_69c6995473348190a4f41d110d619a18 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c7061cbc3c8190a917dd7e71214182 |
completed | March 27, 2026, 10:35 p.m. |
| PD | Predicate disambiguation | batch_69c7015dd8fc8190bc5f52a12bd46209 |
completed | March 27, 2026, 10:14 p.m. |
Created at: March 27, 2026, 3:59 p.m.