Triple
T8787643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Slovakia and Hungary |
E209079
|
entity |
| Predicate | shareBorderLengthApprox |
P85378
|
FINISHED |
| Object | about 654 km |
—
|
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: about 654 km | Statement: [Slovakia and Hungary, shareBorderLengthApprox, about 654 km]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shareBorderLengthApprox Context triple: [Slovakia and Hungary, shareBorderLengthApprox, about 654 km]
-
A.
borderSectionLength
Indicates the measured length of a specific segment of a shared border between two geographic or administrative areas.
-
B.
sharesBorderType
Indicates that two entities are connected by a common boundary characterized by the same specified type of border (e.g., land, river, maritime).
-
C.
relatedBorder
Indicates that two geographic or political entities share a common boundary or border with each other.
-
D.
shareNotableBorderRegion
Indicates that two entities share a common border in a region that is particularly significant or notable (e.g., historically, politically, or geographically).
-
E.
sharesBorderingBody
Indicates that two entities are adjacent to and share the same bordering physical body, such as a landmass, water body, or similar geographic feature.
- 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_69ca836168108190bb43d3dc235c1f55 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f89a84c819085d4cfe4e6dfbda8 |
completed | March 31, 2026, 11:58 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1d48f08190b325a77d4c76d223 |
completed | March 31, 2026, 11:43 p.m. |
| PDg | Predicate description generation | batch_69cc5cfddef48190aee764ee7b25bae9 |
completed | March 31, 2026, 11:47 p.m. |
Created at: March 30, 2026, 6:43 p.m.