Triple

T30192198
Position Surface form Disambiguated ID Type / Status
Subject Empress Xiaozhaoren E767520 entity
Predicate banner P131297 FINISHED
Object Plain Yellow Banner NE NERFINISHED

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: Plain Yellow Banner | Statement: [Empress Xiaozhaoren, banner, Plain Yellow Banner]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: banner
Context triple: [Empress Xiaozhaoren, banner, Plain Yellow Banner]
  • A. bannerType
    Indicates the specific category or style of a banner associated with an entity or context.
  • B. bannerColor
    Indicates the color associated with a banner in the relationship or context described.
  • C. badge
    Indicates that one entity confers, displays, or is associated with a symbolic mark or emblem representing status, achievement, role, or affiliation in relation to another entity.
  • D. bannerAffiliation chosen
    Indicates that an entity is associated with, represented by, or operating under a particular banner, label, or identifying heading.
  • E. brand
    Indicates that one entity is the commercial brand or label under which another entity (such as a product, service, or organization) is marketed or identified.
  • 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_69f2247db1108190835c0727c97637c3 completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f67f84b03c8190a2574fde91d86e8c completed May 2, 2026, 10:49 p.m.
PD Predicate disambiguation batch_69f673c7a4588190837854f3ef61e6bf completed May 2, 2026, 9:59 p.m.
Created at: April 29, 2026, 7:29 p.m.