Triple

T21473298
Position Surface form Disambiguated ID Type / Status
Subject Rubiana E529786 entity
Predicate hasAlternateName P39 FINISHED
Object Ruviana 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: Ruviana | Statement: [Rubiana, hasAlternateName, Ruviana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruviana
Context triple: [Rubiana, hasAlternateName, Ruviana]
  • A. Ruviana chosen
    Ruviana is an alternative name for Roviana, an Oceanic language spoken in the Solomon Islands.
  • B. Ravda
    Ravda is a Bulgarian Black Sea coastal village and resort known for its beaches and proximity to the larger resorts of Nessebar and Sunny Beach.
  • C. Wivina
    Wivina is a feminine given name of likely European origin, notably borne by Belgian politician Wivina Demeester.
  • D. Rehna
    Rehna is a small town in the district of Nordwestmecklenburg in the northern German state of Mecklenburg-Vorpommern.
  • E. Rexena
    Rexena is an alternative name for Rexona, a popular global brand of antiperspirant and deodorant products.
  • 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_69e0c459acb481909bb6ee452a0045c7 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e9ea156dac819087c4594d022d3df6 completed April 23, 2026, 9:44 a.m.
Created at: April 16, 2026, 6:19 p.m.