Triple

T20129765
Position Surface form Disambiguated ID Type / Status
Subject Kanka E490856 entity
Predicate incognitoRole P92521 FINISHED
Object courtier in the court of King Virata 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: courtier in the court of King Virata | Statement: [Kanka, incognitoRole, courtier in the court of King Virata]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: incognitoRole
Context triple: [Kanka, incognitoRole, courtier in the court of King Virata]
  • A. secretRole
    Indicates that an entity holds a role or function that is intentionally hidden or not publicly disclosed within a given context.
  • B. covertRole chosen
    Indicates that an entity holds or performs a hidden, secret, or undercover role in relation to another entity or context.
  • C. exportRole
    Indicates that an entity functions in a capacity or role specifically related to exporting goods, services, or data.
  • D. gammaRole
    Indicates a tertiary or supporting role that an entity plays within a structured hierarchy of roles or participants in an event or relationship.
  • E. ClientRole
    Indicates that an entity participates in a relationship or interaction specifically in the capacity of a client.
  • 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_69da62651a0c8190a3e05e95e056a66b completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e66760b8f08190a66fbb2e9e3925a3 completed April 20, 2026, 5:50 p.m.
PD Predicate disambiguation batch_69e54cfb0d0081908e789b9b57e96668 completed April 19, 2026, 9:45 p.m.
Created at: April 11, 2026, 11:31 p.m.