Triple

T29969843
Position Surface form Disambiguated ID Type / Status
Subject House of Li E761285 entity
Predicate usedGovernmentSystem P168308 FINISHED
Object imperial examination system 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: imperial examination system | Statement: [House of Li, usedGovernmentSystem, imperial examination system]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: usedGovernmentSystem
Context triple: [House of Li, usedGovernmentSystem, imperial examination system]
  • A. usedInGovernmentIn
    Indicates that something is employed, applied, or functions within the context of a specific government or governmental system.
  • B. governmentUseVariant
    Indicates that a government employs or applies an alternative or modified form of something (e.g., a policy, standard, or resource) instead of the primary version.
  • C. underGovernment
    Indicates that one entity is subject to the authority, control, or jurisdiction of a particular government.
  • D. hasGovernmentServicesProvidedBy
    Indicates that one entity receives its governmental services from, or is administratively served by, another entity.
  • E. formedGovernmentUnder
    Indicates that one entity established and operated a governing body under the authority, framework, or auspices of another entity.
  • 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_69f22467626081908d5afea489590e96 completed April 29, 2026, 3:31 p.m.
NER Named-entity recognition batch_69f6786d6e108190b7f631c222899519 completed May 2, 2026, 10:19 p.m.
PD Predicate disambiguation batch_69f66ec8298c8190b41fe9d182c05676 completed May 2, 2026, 9:38 p.m.
PDg Predicate description generation batch_69f67256d064819094be04fc1bbbc635 completed May 2, 2026, 9:53 p.m.
Created at: April 29, 2026, 6:31 p.m.