Triple

T22955286
Position Surface form Disambiguated ID Type / Status
Subject Alessandro Ludovisi E570738 entity
Predicate familyName P18 FINISHED
Object Ludovisi 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: Ludovisi | Statement: [Alessandro Ludovisi, familyName, Ludovisi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ludovisi
Context triple: [Alessandro Ludovisi, familyName, Ludovisi]
  • A. Canova
    Canova was a renowned Italian Neoclassical sculptor celebrated for his marble masterpieces depicting mythological and historical subjects.
  • B. Donnalucata
    Donnalucata is a seaside village in southern Sicily, Italy, known for its sandy beaches, fishing tradition, and role as a holiday destination on the Mediterranean coast.
  • C. Cantalupani
    Cantalupani are the inhabitants of Cantalupo in Sabina, a town in the Lazio region of central Italy.
  • D. Borghese chosen
    Borghese is an influential Italian noble family historically prominent in Roman politics, the Catholic Church, and art patronage.
  • E. Viterelli
    Viterelli is an Italian surname most notably associated with Joe Viterelli, an American character actor known for his mobster roles in films like "Analyze This."
  • 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_69e245b212a88190b5259caf51606084 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f181f09de48190b55913570c965412 completed April 29, 2026, 3:58 a.m.
Created at: April 17, 2026, 3:47 p.m.