Triple
T2357032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eastern Bloc |
E47579
|
entity |
| Predicate | securityServiceModel |
P35862
|
FINISHED |
| Object | Soviet-style secret police |
—
|
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-style secret police | Statement: [Eastern Bloc, securityServiceModel, Soviet-style secret police]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: securityServiceModel Context triple: [Eastern Bloc, securityServiceModel, Soviet-style secret police]
-
A.
securityService
Indicates a relationship where an entity provides or is responsible for protective, safeguarding, or defense-related services for another entity or system.
-
B.
securityModelIdentifier
chosen
Indicates the specific security model or framework under which an entity, interaction, or policy is defined or governed.
-
C.
securityType
Indicates the classification or category of security associated with an entity, such as the type of financial instrument, protection mechanism, or access control applied.
-
D.
securityModelAbbreviation
Indicates that one entity is the standard or commonly used abbreviated form of the name or identifier of a particular security model.
-
E.
securityModelSimilarTo
Indicates that one entity’s security model is similar or comparable to that of another entity.
- 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_69a88a1b678c8190bce986922ba60ce0 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abcb802da08190980100444010f91e |
completed | March 7, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69abc5981ce48190a3f7852d28276e11 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:54 p.m.