Triple
T28173846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North America and Africa |
E715534
|
entity |
| Predicate | formEndpointsOf |
P390
|
FINISHED |
| Object | transatlantic routes |
—
|
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: transatlantic routes | Statement: [North America and Africa, formEndpointsOf, transatlantic routes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formEndpointsOf Context triple: [North America and Africa, formEndpointsOf, transatlantic routes]
-
A.
endPoint
chosen
Indicates the terminal location, limit, or final state reached by an object, process, or path in a given relationship or action.
-
B.
endpointInclusion
Indicates that one endpoint is contained within or is part of another endpoint or endpoint set.
-
C.
typicalEndpoint
Indicates that something represents the standard or commonly used endpoint associated with another entity or process.
-
D.
usesEndpoint
Indicates that one entity accesses or interacts with a specific endpoint to perform an operation or exchange data.
-
E.
endPointExample
Indicates that something serves as a representative or illustrative instance of a particular endpoint.
- 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_69efd6b340f0819095680e15dcdc1830 |
completed | April 27, 2026, 9:35 p.m. |
| NER | Named-entity recognition | batch_69fd884cb2b48190b6acd473430d9e19 |
completed | May 8, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69fd8709ca208190a8bab836f0156af5 |
completed | May 8, 2026, 6:47 a.m. |
Created at: April 27, 2026, 10:14 p.m.