Triple

T13937207
Position Surface form Disambiguated ID Type / Status
Subject The Lady of the Lake E335149 entity
Predicate hasAlias P455 FINISHED
Object Viviane E741555 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: Viviane | Statement: [The Lady of the Lake, hasAlias, Viviane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Viviane
Context triple: [The Lady of the Lake, hasAlias, Viviane]
  • A. Viviane chosen
    Viviane is a legendary enchantress of Arthurian romance, often identified as the Lady of the Lake and known for her role in mentoring and imprisoning the wizard Merlin.
  • B. Luciana
    Luciana is a feminine given name of Latin origin, commonly used in Spanish- and Portuguese-speaking countries.
  • C. Vivianne
    Vivianne is a Dutch professional footballer best known as one of the most prolific forwards in women’s football, starring for Arsenal and the Netherlands national team.
  • D. Alessandra
    Alessandra is an Italian politician, former actress, and granddaughter of Benito Mussolini.
  • E. Alessandra
    Alessandra is an Italian given name, the feminine form of Alessandro, equivalent to Alexandra in English.
  • 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_69d81c5f739081908bc05b2461f54828 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2cf42878819085146670d7b92605 completed April 14, 2026, 12:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd5bb227b48190bed1d19b8066b283 completed May 8, 2026, 3:42 a.m.
Created at: April 9, 2026, 10:17 p.m.