Triple

T20870397
Position Surface form Disambiguated ID Type / Status
Subject Don Matteo E513872 entity
Predicate hasProtagonist P8706 FINISHED
Object Don Matteo Bondini 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: Don Matteo Bondini | Statement: [Don Matteo, hasProtagonist, Don Matteo Bondini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Don Matteo Bondini
Context triple: [Don Matteo, hasProtagonist, Don Matteo Bondini]
  • A. Don Matteo Bondini chosen
    Don Matteo Bondini is a fictional Italian Catholic priest and amateur detective who solves crimes while offering moral guidance in the long-running TV series "Don Matteo."
  • B. Mario Lanfranchi
    Mario Lanfranchi was an Italian film and television director and producer, known for his work in opera productions and for his marriage to soprano Anna Moffo.
  • C. Enzo Rossi
    Enzo Rossi is the son of American actress Patricia Arquette and musician Paul Rossi.
  • D. Enzo Esposito
    Enzo Esposito is an individual notable enough to be recognized as a prominent bearer of the surname Esposito.
  • E. Angelo Errichetti
    Angelo Errichetti was an American politician and former mayor of Camden, New Jersey, best known for his central role in the Abscam political corruption scandal of the late 1970s.
  • 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_69e0b4f675cc8190b4e745225b62eb66 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c4637ec48190830023d20fb8124c completed April 21, 2026, 12:27 a.m.
Created at: April 16, 2026, 12:45 p.m.