Triple

T24717291
Position Surface form Disambiguated ID Type / Status
Subject Flag of Paraguay E612196 entity
Predicate reverseSealFeatures P157197 FINISHED
Object inscription PAZ Y JUSTICIA 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: inscription PAZ Y JUSTICIA | Statement: [Flag of Paraguay, reverseSealFeatures, inscription PAZ Y JUSTICIA]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: reverseSealFeatures
Context triple: [Flag of Paraguay, reverseSealFeatures, inscription PAZ Y JUSTICIA]
  • A. reverseSealFeatures chosen
    Indicates that the direction or orientation of seal-related features is inverted or swapped relative to a reference configuration.
  • B. reverseFeature
    Indicates that one feature is the inverse or opposite counterpart of another feature in a given context.
  • C. reverseInscription
    Indicates that one entity is inscribed as the reverse or mirror image of another entity’s inscription.
  • D. secondSealAssociatedWith
    Indicates an associative relationship in which something is linked or connected specifically to a second seal.
  • E. usedSeal
    Indicates that an entity has applied or employed a seal (e.g., for closure, authentication, or protection) on another entity.
  • 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_69e2d7d6e7a48190bb43b0d8bb1137a0 completed April 18, 2026, 1:01 a.m.
NER Named-entity recognition batch_69f464b4c9b0819085daa00c7c3b8b76 completed May 1, 2026, 8:30 a.m.
PD Predicate disambiguation batch_69f45cf017a88190b4985b11159c907d completed May 1, 2026, 7:57 a.m.
Created at: April 18, 2026, 3:38 a.m.