Triple

T22832042
Position Surface form Disambiguated ID Type / Status
Subject Jacinta Marto E565827 entity
Predicate givenName P17 FINISHED
Object Jacinta 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: Jacinta | Statement: [Jacinta Marto, givenName, Jacinta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jacinta
Context triple: [Jacinta Marto, givenName, Jacinta]
  • A. Jacinta chosen
    Jacinta is a feminine given name of Spanish and Portuguese origin, famously borne by Jacinta Marto, one of the child visionaries of Fátima.
  • B. Ondina
    Ondina is a traditional female character featured in the Viareggio Carnival, often embodying the festive, allegorical spirit of this famous Italian celebration.
  • C. Aleta
    Aleta is a central character in the Prince Valiant saga, known as the intelligent and noble Queen of the Misty Isles and the beloved wife of the hero Prince Valiant.
  • D. Soléa
    Soléa is the public transport operator responsible for managing and running the urban bus and tram network in Mulhouse, France.
  • E. Faina
    Faina is a feminine given name, notably borne by the celebrated Soviet actress Faina Ranevskaya.
  • 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_69e24585ab1c81909b2b5065d15805d5 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e2c8d3881909eb19d65187ed719 completed April 29, 2026, 3:42 a.m.
Created at: April 17, 2026, 3:34 p.m.