Triple

T5007608
Position Surface form Disambiguated ID Type / Status
Subject Turnus E112534 entity
Predicate betrothedTo P33561 FINISHED
Object Lavinia E388975 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: Lavinia | Statement: [Turnus, betrothedTo, Lavinia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lavinia
Context triple: [Turnus, betrothedTo, Lavinia]
  • A. Lavinia chosen
    Lavinia is a novel by Ursula K. Le Guin that reimagines the life of the minor Aeneid character Lavinia, giving her a rich inner world and narrative voice.
  • B. Felicitas
    Felicitas is a feminine given name of Latin origin, associated with good fortune and happiness and historically linked to the Roman goddess of luck and success.
  • C. Cloelia
    Cloelia was a Roman woman known primarily as one of the wives of the powerful late Republican dictator Lucius Cornelius Sulla.
  • D. Corinna
    Corinna was an ancient Greek lyric poet from Boeotia, renowned for her choral poetry composed in the Aeolic dialect.
  • E. Lucilla
    Lucilla was a Roman imperial princess and daughter of Emperor Marcus Aurelius who became Empress as the wife of Lucius Verus and was later implicated in a plot against her brother Commodus.
  • 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_69bd4433d0b08190877e83959ef40d81 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd72e8a0308190a47d81943ad85bba completed March 20, 2026, 4:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9266314881909dfb710c5b5c8f65 completed March 21, 2026, 12:43 p.m.
Created at: March 20, 2026, 1:35 p.m.