Triple
T24520928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hawaii Belt Road |
E606523
|
entity |
| Predicate | routeAround |
P151412
|
FINISHED |
| Object | Island of Hawaii coastline |
—
|
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: Island of Hawaii coastline | Statement: [Hawaii Belt Road, routeAround, Island of Hawaii coastline]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: routeAround Context triple: [Hawaii Belt Road, routeAround, Island of Hawaii coastline]
-
A.
routeAlong
chosen
Indicates that one entity follows, runs parallel to, or is situated along the course or path defined by another entity.
-
B.
routeVia
Indicates that a connection, path, or communication between two points is established or carried out through an intermediate location, node, or channel.
-
C.
routeBetween
Indicates that there exists a path or connection enabling travel or communication between two locations or points.
-
D.
routePlan
Indicates a planned path or sequence of steps for traveling from a starting point to a destination.
-
E.
routeOf
Indicates that one entity is the path, course, or trajectory taken or followed by another entity (such as a vehicle, shipment, or signal).
- 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_69e2c4c85778819085f5da9af3569ad5 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2be044d4c819094e14eda28d371a7 |
completed | April 30, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b0ca8081908d931aec560eae56 |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:24 a.m.