Triple

T8902997
Position Surface form Disambiguated ID Type / Status
Subject Mariana in the South E211974 entity
Predicate mainSubject P3 FINISHED
Object Mariana E715958 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: Mariana | Statement: [Mariana in the South, mainSubject, Mariana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mariana
Context triple: [Mariana in the South, mainSubject, Mariana]
  • A. Mariana
    "Mariana" is a famous 1851 Pre-Raphaelite painting by John Everett Millais depicting a solitary woman in a richly detailed interior, inspired by Shakespeare’s "Measure for Measure" and Tennyson’s poem of the same name.
  • B. Mariana
    Mariana is a neighborhood (barrio) within the city of Dorado, Puerto Rico.
  • C. Mariana chosen
    Mariana is a historic colonial-era city in the Brazilian state of Minas Gerais, known for its baroque architecture and gold-mining heritage.
  • D. Galoa
    Galoa is a small coastal village located on Kadavu Island in Fiji, known for its traditional Fijian lifestyle and surrounding natural beauty.
  • E. Ceilândia
    Ceilândia is a populous administrative region of Brazil’s Federal District, known for its working-class character, vibrant street markets, and strong cultural identity rooted in northeastern Brazilian traditions.
  • 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_69ca839255248190b43984294abd92ae completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc64c091d08190b59e54eb4a184e41 completed April 1, 2026, 12:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfac1b03808190b4672da5b292e12b completed April 3, 2026, 12:01 p.m.
Created at: March 30, 2026, 6:55 p.m.