Triple

T20774541
Position Surface form Disambiguated ID Type / Status
Subject Christian De Sica E511320 entity
Predicate mother P120 FINISHED
Object María Mercader 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: María Mercader | Statement: [Christian De Sica, mother, María Mercader]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: María Mercader
Context triple: [Christian De Sica, mother, María Mercader]
  • A. María Mercader chosen
    María Mercader was a Spanish-born actress best known for her work in Italian cinema and her long association with renowned director Vittorio De Sica.
  • B. María Cardeña
    María Cardeña was the wife of German-Mexican photographer Guillermo Kahlo and a member of the extended family connected to artist Frida Kahlo.
  • C. Luisa Cortés
    Luisa Cortés is a figure known primarily for her association with Julio Zapata, about whom limited public biographical information is available.
  • D. Luisa Cervera
    Luisa Cervera is a notable individual who carries the Cervera surname, recognized as a distinguished bearer of that family name.
  • E. María Cortés
    María Cortés was a daughter of the Spanish conquistador Hernán Cortés, belonging to the colonial-era lineage that emerged from his conquests in the Americas.
  • 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_69e0b4ca01148190ac018e57e0cab46f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c26a39bc81909ca5d102056d8586 completed April 21, 2026, 12:18 a.m.
Created at: April 16, 2026, 12:37 p.m.