Triple

T21812421
Position Surface form Disambiguated ID Type / Status
Subject Leonor Watling E538511 entity
Predicate givenName P17 FINISHED
Object Leonor 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: Leonor | Statement: [Leonor Watling, givenName, Leonor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Leonor
Context triple: [Leonor Watling, givenName, Leonor]
  • A. Leonor chosen
    Leonor is the given name of Leonor Fini, a renowned Argentine-Italian surrealist painter and designer known for her fantastical, often erotic imagery and strong, unconventional female figures.
  • B. Leonor de Guzmán
    Leonor de Guzmán was a Spanish noblewoman of the 16th century, known for her connections to prominent aristocratic families in the Kingdom of Castile.
  • C. Isabelita
    Isabelita is the nickname of Isabel Perón, the former president of Argentina and the world's first female president.
  • D. Enriqueta
    Enriqueta is a feminine given name of Spanish origin, often associated with historical and cultural figures in Spanish-speaking countries.
  • E. Princess of Navarre
    Princess of Navarre was the French royal title held by Catherine de Bourbon, a prominent Huguenot noblewoman and sister of King Henry IV of France.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e0c473f0f8819086c9d1b4a143bd67 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f07cc7ec1c8190a5420b44a49ae32f completed April 28, 2026, 9:24 a.m.
Created at: April 16, 2026, 6:53 p.m.