Triple

T14062745
Position Surface form Disambiguated ID Type / Status
Subject Rani E338385 entity
Predicate scriptInBengali P76566 FINISHED
Object রানি E71377 NE FINISHED

How this triple was built (3 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: রানি | Statement: [Rani, scriptInBengali, রানি]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: রানি
Context triple: [Rani, scriptInBengali, রানি]
  • A. Raja Eleena
    Raja Eleena is a Malaysian royal princess, known as one of the daughters of the late Sultan Azlan Shah of Perak.
  • B. Queen La
    Queen La is a recurring villainess in the Tarzan stories, depicted as the powerful and often sinister queen and high priestess of the lost city of Opar.
  • C. Rainha Má
    Rainha Má is a popular Brazilian song by Daniela Mercury that helped solidify her status as a leading figure in axé music in the 1990s.
  • D. the Rani chosen
    The Rani is a brilliant but ruthless renegade Time Lord and recurring villain in the Doctor Who universe, known for her coldly scientific experiments and amoral pursuit of knowledge.
  • E. People’s Princess
    The "People’s Princess" is a widely used media nickname for Diana, Princess of Wales, highlighting her popularity, compassion, and close connection with the public.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: scriptInBengali
Context triple: [Rani, scriptInBengali, রানি]
  • A. titleInBengaliScript chosen
    Indicates that the title of an entity is written or represented in the Bengali script.
  • B. scriptBasis
    Indicates that one script is based on, derived from, or adapted from another script.
  • C. script
    Indicates that an entity is associated with a written text or code (such as a screenplay, program, or written instructions) that defines its content or behavior.
  • D. nameInBengali
    Indicates that an entity’s name is expressed in the Bengali language.
  • E. scriptedAs
    Indicates that one entity is written or programmed to behave, appear, or function in the manner defined by another entity (such as a script, role, or specification).
  • F. None of above.

Provenance (4 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de568876308190840361dcaf10bd45 completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcb6673de881909653c7691422b800 completed May 7, 2026, 3:57 p.m.
PD Predicate disambiguation batch_69de05adef888190b023ab42ef5076b6 completed April 14, 2026, 9:15 a.m.
Created at: April 9, 2026, 10:21 p.m.