Triple
T37399000
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Federal Charter of 1291 |
E928938
|
entity |
| Predicate | countryOfArchive |
P204271
|
FINISHED |
| Object | Switzerland |
E5030
|
NE 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: Switzerland | Statement: [Federal Charter of 1291, countryOfArchive, Switzerland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfArchive Context triple: [Federal Charter of 1291, countryOfArchive, Switzerland]
-
A.
countryOf
Indicates that one entity is the country to which another entity belongs, is located in, or is associated with.
-
B.
acquisitionCountry
Indicates the country in which the acquisition of an entity or asset took place.
-
C.
countryOfRelease
Indicates the country in which an item (such as a product, work, or media) was officially released.
-
D.
laterCountryOfOrigin
Indicates that an entity’s country of origin changed, and this predicate specifies the country that became its origin at a later time than a previously associated country.
-
E.
creationCountry
Indicates the country in which an entity was originally created, produced, or brought into existence.
- F. None of above. chosen
Provenance (5 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_69f76ebbf79c8190b85bbcf3a6be57e4 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a035b78140081908e451cb63d3c1c7c |
completed | May 12, 2026, 4:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4076f531308190824c845656c82c11 |
completed | June 28, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_6a035af3d8f48190bf1f3741d374404e |
completed | May 12, 2026, 4:53 p.m. |
| PDg | Predicate description generation | batch_6a035b773898819099125a5efc239d3e |
completed | May 12, 2026, 4:55 p.m. |
Created at: May 3, 2026, 4:16 p.m.