Triple

T19968500
Position Surface form Disambiguated ID Type / Status
Subject Princess Januária of Brazil E480006 entity
Predicate givenName P17 FINISHED
Object Januária 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: Januária | Statement: [Princess Januária of Brazil, givenName, Januária]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Januária
Context triple: [Princess Januária of Brazil, givenName, Januária]
  • A. Januária chosen
    Januária was a Brazilian princess of the Empire of Brazil, daughter of Emperor Pedro I and heir presumptive before the birth of her younger brother Pedro II.
  • B. Meámbar
    Meámbar is a town and municipality located in the Comayagua Department of central Honduras.
  • C. Marcho
    Marcho is a hobbit from J.R.R. Tolkien’s legendarium who, along with his brother Blanco, is credited with leading the hobbits across the River Baranduin and establishing their homeland in the Shire.
  • D. Iulis
    Iulis is an ancient Greek city, historically known as Ioulis, located on the island of Kea in the Cyclades.
  • E. Maio
    Maio is one of the main islands of Cape Verde, known for its quiet beaches, salt flats, and relatively flat, arid landscape.
  • 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_69d8e523c19881909f9197037200dde6 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65bc6b0208190b1ae30be95712326 completed April 20, 2026, 5 p.m.
Created at: April 10, 2026, 1:54 p.m.