Triple

T20653682
Position Surface form Disambiguated ID Type / Status
Subject Andrade E507566 entity
Predicate hasVariant P455 FINISHED
Object d’Andrade 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: d’Andrade | Statement: [Andrade, hasVariant, d’Andrade]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: d’Andrade
Context triple: [Andrade, hasVariant, d’Andrade]
  • A. Andrade chosen
    Andrade is a common Portuguese and Spanish surname borne by numerous notable figures across fields such as sports, politics, and the arts.
  • B. Abel de Andrade
    Abel de Andrade is a Portuguese designer best known for creating the modern flag of the Madeira archipelago.
  • C. Malu Verçosa
    Malu Verçosa is a Brazilian journalist and LGBTQ+ activist best known as the wife of singer Daniela Mercury and for their public role in advancing same-sex marriage visibility in Brazil.
  • D. do Amaral
    do Amaral is the surname of Tarsila do Amaral, a pioneering Brazilian modernist painter and key figure in Latin American art.
  • E. Paulo Campos
    Paulo Campos is a screenwriter best known for co-writing the film adaptation of the psychological thriller "The Devil All the Time."
  • 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_69e0b4bf58c081908e52a4500e03ff83 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b2eb8c7081908e7dd7f7fa375190 completed April 20, 2026, 11:12 p.m.
Created at: April 16, 2026, 11:43 a.m.