Triple
T17689270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Race to the Sea |
E440980
|
entity |
| Predicate | frontExtendedFrom |
P128582
|
FINISHED |
| Object | Swiss border |
—
|
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: Swiss border | Statement: [Race to the Sea, frontExtendedFrom, Swiss border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frontExtendedFrom Context triple: [Race to the Sea, frontExtendedFrom, Swiss border]
-
A.
frontType
Indicates the type or category of a front (e.g., boundary or leading side) that one entity presents or forms relative to another.
-
B.
extendedFrom
Indicates that one entity is derived by adding to or building upon the scope, content, or structure of another entity.
-
C.
frontOf
Indicates that one entity is positioned directly before another along a primary viewing or movement direction.
-
D.
frontLength
Indicates the length measurement of the front side or edge of an object relative to its overall dimensions.
-
E.
formerExtension
Indicates that one entity previously served as an extension or subsidiary part of another entity, but no longer holds that status.
- 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_69d8b9e940b081908b862bb0e6e89b0d |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4704a6bb4819083752285baf3b3ee |
completed | April 19, 2026, 6:03 a.m. |
| PD | Predicate disambiguation | batch_69e3cde3673c8190a889e14ba1f07dc1 |
completed | April 18, 2026, 6:30 p.m. |
| PDg | Predicate description generation | batch_69e3cfaac2b881909e1140339eb1a0dd |
completed | April 18, 2026, 6:38 p.m. |
Created at: April 10, 2026, 10:03 a.m.