Triple

T2492400
Position Surface form Disambiguated ID Type / Status
Subject Roxane E52073 entity
Predicate hasVariant P455 FINISHED
Object Roxana E66871 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: Roxana | Statement: [Roxane, hasVariant, Roxana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roxana
Context triple: [Roxane, hasVariant, Roxana]
  • A. Roxana chosen
    Roxana is a feminine given name of Persian origin, historically associated with figures such as the wife of Alexander the Great and later borne by various notable women.
  • B. Leonora
    Leonora is a feminine given name used in various cultures, often considered a variant of Eleanor or Leonore.
  • C. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • D. Valeria
    Valeria was a Roman imperial princess and later empress, best known as the daughter of Emperor Diocletian and for her tragic fate during the political turmoil of the Tetrarchy.
  • E. Valeria
    Valeria was a Roman noblewoman best known as the last wife of the dictator Lucius Cornelius Sulla during the late Roman Republic.
  • 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_69ab4955111c8190835bf619adec21ff completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd192cad08190b13bf8e2d7149199 completed March 7, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69af1f93a29081908de1107bf0f96647 completed March 9, 2026, 7:29 p.m.
Created at: March 6, 2026, 9:45 p.m.