Triple
T37008373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Navassa Island Light |
E915868
|
entity |
| Predicate | servesShippingRoutesBetween |
P202181
|
FINISHED |
| Object | North America and South America |
—
|
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: North America and South America | Statement: [Navassa Island Light, servesShippingRoutesBetween, North America and South America]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesShippingRoutesBetween Context triple: [Navassa Island Light, servesShippingRoutesBetween, North America and South America]
-
A.
containsShippingRoute
Indicates that one location or area includes within its boundaries a shipping route used for transporting goods or vessels.
-
B.
shippingLaneFor
Indicates that one entity serves as a designated shipping lane or route used for the transportation or navigation of another entity (such as ships or cargo).
-
C.
servesCarrier
Indicates that one entity provides carrier services or functions as a carrier on behalf of another entity.
-
D.
hasNearbyShippingLane
Indicates that there is a shipping lane located close to the referenced entity or area.
-
E.
servesRegionAcrossFrom
Indicates that a service or entity operates in a region that is geographically located directly across from another specified region.
- 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_69f76e90ed548190b187d2475f5c807d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a005d878aec81908e1177914a8fb610 |
completed | May 10, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_6a005c382f8881908ff33ebb7f88c430 |
completed | May 10, 2026, 10:21 a.m. |
| PDg | Predicate description generation | batch_6a005d86d6e481909e9f6ae81568cfb8 |
completed | May 10, 2026, 10:27 a.m. |
Created at: May 3, 2026, 4:14 p.m.