Triple
T245703
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Molotov–Ribbentrop Pact |
E5031
|
entity |
| Predicate | archivalEvidence |
P3650
|
FINISHED |
| Object | Soviet archives |
—
|
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: Soviet archives | Statement: [Molotov–Ribbentrop Pact, archivalEvidence, Soviet archives]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: archivalEvidence Context triple: [Molotov–Ribbentrop Pact, archivalEvidence, Soviet archives]
-
A.
archivesType
Indicates that one entity serves as an archival record or stored version of another entity, specifying the type or category of that archived content.
-
B.
providesEvidenceFor
chosen
Indicates that one entity serves as support, justification, or proof for the validity or truth of another entity.
-
C.
preservedAt
Indicates that something is kept, maintained, or conserved in a particular place or context.
-
D.
usedEvidenceType
Indicates that a particular type or category of evidence was employed or relied upon in a given context or activity.
-
E.
hasDigitalArchive
Indicates that an entity maintains or is associated with a collection of materials stored in a digital archive.
- 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_69a257c4bf688190a46ebbf411ab7473 |
completed | Feb. 28, 2026, 2:49 a.m. |
| NER | Named-entity recognition | batch_69a25d128c0081909908825b302ae635 |
completed | Feb. 28, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69a25b63b0bc8190864d7324d339fb48 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:54 a.m.