Triple
T28939557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A180 highway |
E730407
|
entity |
| Predicate | hasEndpointAtBorder |
P27716
|
FINISHED |
| Object | Russian–Estonian border |
—
|
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: Russian–Estonian border | Statement: [A180 highway, hasEndpointAtBorder, Russian–Estonian border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasEndpointAtBorder Context triple: [A180 highway, hasEndpointAtBorder, Russian–Estonian border]
-
A.
hasBorderTerminus
chosen
Indicates that one entity serves as the endpoint or terminal location of another entity’s border or boundary.
-
B.
hasBorderConnection
Indicates that two regions or entities share a common boundary or are directly connected along a border.
-
C.
liesOnBorderOf
Indicates that one entity is located along or directly adjacent to the boundary line separating it from another entity.
-
D.
hasBorderCheckpointOnOtherSide
Indicates that a border checkpoint is located on the opposite side of a boundary relative to a referenced point or entity.
-
E.
isBoundaryFor
Indicates that one entity serves as the limiting edge, border, or enclosing extent that defines the spatial or conceptual bounds of another entity.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f71f8ee0688190bd025f27993452d3 |
completed | May 3, 2026, 10:12 a.m. |
| PD | Predicate disambiguation | batch_69f71cc405c08190863565609a4c8499 |
completed | May 3, 2026, 10 a.m. |
Created at: April 28, 2026, 8:35 a.m.