Triple
T27029640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Metz–Saarbrücken railway |
E680882
|
entity |
| Predicate | hasBorderSection |
P69484
|
FINISHED |
| Object | Franco-German 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: Franco-German border | Statement: [Metz–Saarbrücken railway, hasBorderSection, Franco-German border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasBorderSection Context triple: [Metz–Saarbrücken railway, hasBorderSection, Franco-German border]
-
A.
hasBorderElement
chosen
Indicates that one entity includes or is associated with another entity that forms part of its boundary or edge.
-
B.
hasBorderThrough
Indicates that a border between two regions or entities passes through or along a specified intermediate area, feature, or object.
-
C.
borderSectionOf
Indicates that one entity represents a specific segment or portion of the overall border of another entity.
-
D.
hasBorderCode
Indicates that there is an associated code or identifier specifying the type or status of a border between entities.
-
E.
hadBorderType
Indicates that a boundary between two entities existed and specifies the nature or classification of that border (e.g., land, maritime, disputed).
- 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_69eeeb5566f08190813daf896fa3da04 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f6c1265c208190aacd2b551f8f0f82 |
completed | May 3, 2026, 3:29 a.m. |
| PD | Predicate disambiguation | batch_69f6bd2415fc81908c23c311aebce66f |
completed | May 3, 2026, 3:12 a.m. |
Created at: April 27, 2026, 7:13 a.m.