Triple

T27154543
Position Surface form Disambiguated ID Type / Status
Subject posadnik of Novgorod E682484 entity
Predicate typicalOfficeHolderClass P15556 FINISHED
Object boyar aristocracy 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: boyar aristocracy | Statement: [posadnik of Novgorod, typicalOfficeHolderClass, boyar aristocracy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: typicalOfficeHolderClass
Context triple: [posadnik of Novgorod, typicalOfficeHolderClass, boyar aristocracy]
  • A. officeHolderClass chosen
    Indicates that a given role or position is held by members belonging to a specified class or category of office holders.
  • B. typicalOfficeHolderTitle
    Indicates the standard or commonly used title typically held by the office holder of a given position or role.
  • C. officeHolderTypicallyFrom
    Indicates that the person holding a particular office is typically drawn from or originates from a specified group, region, or category.
  • D. officeHolderUsually
    Indicates that an entity is the person who typically or customarily holds a particular office or position.
  • E. officeHoldersAreUsually
    Indicates that individuals holding a particular office or position are typically or generally characterized by a specified property or role.
  • 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_69eefaceb2a08190b9659b7f730629f5 completed April 27, 2026, 5:57 a.m.
NER Named-entity recognition batch_69ff8cecbf048190860b9f72b8753f5c completed May 9, 2026, 7:37 p.m.
PD Predicate disambiguation batch_69ff8c4c39dc8190b5bf35adc1bae7c6 completed May 9, 2026, 7:34 p.m.
Created at: April 27, 2026, 9:15 a.m.