Triple

T17621191
Position Surface form Disambiguated ID Type / Status
Subject Lucretia E429711 entity
Predicate title P38 FINISHED
Object Domina 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: Domina | Statement: [Lucretia, title, Domina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Domina
Context triple: [Lucretia, title, Domina]
  • A. Domina chosen
    Domina is a historical drama television series that chronicles the life and political rise of Livia Drusilla in ancient Rome.
  • B. Domina
    Domina is a domineering and sharp-tongued Roman matron in the musical farce "A Funny Thing Happened on the Way to the Forum."
  • C. Mara of Rome
    Mara of Rome is a character from the Italian anthology film "Yesterday, Today and Tomorrow," appearing in one of its episodic stories set in Rome.
  • D. Valeria Victrix
    Valeria Victrix was the honorific title of the Roman Empire’s Legio XX, a legion distinguished for its valor and victories, particularly in the conquest and defense of Roman Britain.
  • E. Vita Caracallae
    Vita Caracallae is a biography of the Roman emperor Caracalla found within the late antique Latin collection of imperial lives known as the Historia Augusta.
  • 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_69d889e37f308190a6aa0a69daff86c7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e46d36074481909ee79e238841edf2 completed April 19, 2026, 5:50 a.m.
Created at: April 10, 2026, 5:51 a.m.