Triple
T29820021
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poland–Belarus border |
E757218
|
entity |
| Predicate | isCustomsBorderOf |
P167903
|
FINISHED |
| Object | European Union |
—
|
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: European Union | Statement: [Poland–Belarus border, isCustomsBorderOf, European Union]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCustomsBorderOf Context triple: [Poland–Belarus border, isCustomsBorderOf, European Union]
-
A.
borderingAuthorityOf
Indicates that one authority’s jurisdiction directly touches or shares a boundary with another authority’s jurisdiction.
-
B.
hasBorderPostWith
Indicates that two regions or territories share a border where an official border post or checkpoint is located between them.
-
C.
borderStateOf
Indicates that one state shares a common boundary or border with another state.
-
D.
hasBorderTerminusCountry
Indicates that a country serves as the endpoint or boundary limit of a border segment associated with another entity.
-
E.
hasBorderWithinCountry
Indicates that one region or area shares an internal boundary with another region or area within the same country.
- 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_69f2245701c88190ad42415a0956c4ed |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69f6756645d48190a1645d578759dccd |
completed | May 2, 2026, 10:06 p.m. |
| PD | Predicate disambiguation | batch_69f66ac1a4fc81909740d2e52fbe6970 |
completed | May 2, 2026, 9:21 p.m. |
| PDg | Predicate description generation | batch_69f66c59de9881909ebbb7b0ae7ab495 |
completed | May 2, 2026, 9:27 p.m. |
Created at: April 29, 2026, 5:28 p.m.