Triple

T16035082
Position Surface form Disambiguated ID Type / Status
Subject Kino E388950 entity
Predicate hasSpouse P13 FINISHED
Object Juana 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: Juana | Statement: [Kino, hasSpouse, Juana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Juana
Context triple: [Kino, hasSpouse, Juana]
  • A. Juana
    Juana is the Spanish feminine given name equivalent to Jane, commonly used in Spanish-speaking cultures.
  • B. Juana de Guardo
    Juana de Guardo was the wife of the famed Spanish playwright and poet Lope de Vega, known primarily through her marriage into his life and literary history.
  • C. Juana Díaz
    Juana Díaz is a municipality on the southern coast of Puerto Rico known for its agricultural traditions and historic town center.
  • D. Juana Lorenza Gómez de Sandoval y Rojas
    Juana Lorenza Gómez de Sandoval y Rojas was a Spanish noblewoman of the powerful Sandoval and Rojas families and the daughter of Luisa de Guzmán, queen consort of Portugal.
  • E. Juana Enríquez
    Juana Enríquez was a 15th-century Queen of Aragon and Navarre, notable as the consort of John II of Aragon and the mother of King Ferdinand II, a key architect of Spanish unification.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide. chosen

Provenance (2 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_69d86dada3808190825d5f80d72fbe88 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e1833b84608190887dafda5d081dc0 completed April 17, 2026, 12:47 a.m.
Created at: April 10, 2026, 4:56 a.m.