Triple

T13914482
Position Surface form Disambiguated ID Type / Status
Subject Radwan coat of arms E334582 entity
Predicate hasHeraldicOrientation P112266 FINISHED
Object banner upright 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: banner upright | Statement: [Radwan coat of arms, hasHeraldicOrientation, banner upright]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasHeraldicOrientation
Context triple: [Radwan coat of arms, hasHeraldicOrientation, banner upright]
  • A. hasHeraldicAttitude
    Indicates that an entity (typically an animal or figure in heraldry) is depicted with a specific standardized posture or stance in a coat of arms.
  • B. heraldicAspect
    Indicates a relationship where one entity serves as a heraldic feature, attribute, or component in the coat of arms or heraldic representation of another entity.
  • C. hasHeraldicShieldShape
    Indicates that an entity’s heraldic shield is characterized by a specific geometric or stylistic shape.
  • D. hasHeraldryType
    Indicates that an entity is associated with a specific category or style of heraldry (such as a type of coat of arms or emblem).
  • E. hasHeraldicBasis
    Indicates that something is founded on, derived from, or justified by heraldic principles, symbols, or traditions.
  • 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_69d81c5eaa9c819083b1ff8689179565 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de27245c648190b2946845ce0fdbf8 completed April 14, 2026, 11:38 a.m.
PD Predicate disambiguation batch_69de059e4ba881908554f72e889719fa completed April 14, 2026, 9:15 a.m.
PDg Predicate description generation batch_69de239524688190a0f2408c239cfcaa completed April 14, 2026, 11:23 a.m.
Created at: April 9, 2026, 10:16 p.m.