Triple
T28948625
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Dakota–Minnesota border |
E730946
|
entity |
| Predicate | westernSideState |
P166517
|
FINISHED |
| Object | North Dakota |
—
|
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: North Dakota | Statement: [North Dakota–Minnesota border, westernSideState, North Dakota]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: westernSideState Context triple: [North Dakota–Minnesota border, westernSideState, North Dakota]
-
A.
westernTerminusState
Indicates the state in which something (such as a route, line, or path) has its western endpoint or terminus.
-
B.
westernTerminusConnectsTo
Indicates that the western endpoint or terminus of one route, line, or path is directly connected to another specified route, line, or location.
-
C.
easternSideState
Indicates that a state or region is located on, or corresponds to, the eastern side of a specified reference area or boundary.
-
D.
westernTerminusNear
Indicates that the western endpoint of one entity is located close to another entity.
-
E.
locatedWestOf
Indicates that one entity is positioned geographically to the west of another entity.
- 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_69f043eb9bcc819091ac7b07aecb6475 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6622808b48190bbabcc75288ab031 |
completed | May 2, 2026, 8:44 p.m. |
| PD | Predicate disambiguation | batch_69f660f082508190a95a7888ad66cb2e |
completed | May 2, 2026, 8:39 p.m. |
| PDg | Predicate description generation | batch_69f6617a7e7c81908cfac4a2250797ee |
completed | May 2, 2026, 8:41 p.m. |
Created at: April 28, 2026, 8:42 a.m.