Triple

T1170263
Position Surface form Disambiguated ID Type / Status
Subject Escola Nacional de Belas Artes E24894 entity
Predicate hasNotableAlumni P51 FINISHED
Object Adriana Varejão E135154 NE 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: Adriana Varejão | Statement: [Escola Nacional de Belas Artes, hasNotableAlumni, Adriana Varejão]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adriana Varejão
Context triple: [Escola Nacional de Belas Artes, hasNotableAlumni, Adriana Varejão]
  • A. Fernanda Tadeu
    Fernanda Tadeu is a Portuguese educator and public figure best known as the wife of former Prime Minister António Costa.
  • B. Manuela Veloso
    Manuela Veloso is a prominent computer scientist and roboticist known for her pioneering work in artificial intelligence and multi-agent robotics.
  • C. Mariana Teixeira de Carvalho
    Mariana Teixeira de Carvalho is a Brazilian lawyer best known as the wife of U2 bassist Adam Clayton.
  • D. Beatriz Milhazes chosen
    Beatriz Milhazes is a Brazilian contemporary artist renowned for her vibrant, large-scale abstract paintings that blend modernist geometry with motifs from Brazilian culture and decorative arts.
  • E. Maria Azevêdo
    Maria Azevêdo is known as the wife of Brazilian diplomat Roberto Azevêdo, former Director-General of the World Trade Organization.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69a494082a7c819095004f423f294a64 completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4bce972cc8190bce0b77cfda6da41 completed March 1, 2026, 10:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac7645abc8819086de42185bd403ed completed March 7, 2026, 7:02 p.m.
Created at: March 1, 2026, 7:45 p.m.