Triple

T16367745
Position Surface form Disambiguated ID Type / Status
Subject O Primo Basílio E397478 entity
Predicate mainCharacter P1183 FINISHED
Object Luísa E44829 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: Luísa | Statement: [O Primo Basílio, mainCharacter, Luísa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Luísa
Context triple: [O Primo Basílio, mainCharacter, Luísa]
  • A. Luisa chosen
    Luisa is a feminine given name used in various languages, particularly Romance languages, as a form of the name Louise.
  • B. Eugênia
    Eugênia is a Portuguese given name, equivalent to Eugenia, commonly used in Brazil and other Lusophone countries.
  • C. Margarida
    Margarida is a given name, commonly used in Portuguese and Catalan, that corresponds to the English name Margaret.
  • D. Maria Francesca
    Maria Francesca of Savoy was an 18th-century Italian princess of the House of Savoy who became Landgravine of Hesse-Rotenburg through marriage.
  • E. Isabella
    Isabella was a Polish princess of the Jagiellonian dynasty who became Queen consort of Hungary in the 16th century.
  • 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_69d87f2778dc8190aa95c7572db127e6 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2ff3f0694819097faa1c1447a9e97 completed April 18, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a002dc29f088190ba5d69ff3c12a251 completed May 10, 2026, 7:03 a.m.
Created at: April 10, 2026, 5:08 a.m.