Triple

T21535835
Position Surface form Disambiguated ID Type / Status
Subject San Marco, Florence E531345 entity
Predicate hasPart P35 FINISHED
Object San Marco convent 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: San Marco convent | Statement: [San Marco, Florence, hasPart, San Marco convent]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: San Marco convent
Context triple: [San Marco, Florence, hasPart, San Marco convent]
  • A. Convent of San Marco chosen
    The Convent of San Marco is a historic Dominican monastery in Florence, Italy, renowned for its Fra Angelico frescoes and its association with the reformer Girolamo Savonarola.
  • B. San Marco church
    San Marco church is a historic Christian church located in the Sicilian city of Enna, Italy.
  • C. San Domenico church
    San Domenico church is a historic Roman Catholic church in Città di Castello, Italy, noted for its medieval origins and artistic heritage.
  • D. San Domenico Maggiore
    San Domenico Maggiore is a prominent Gothic-style church and former Dominican convent in Naples, Italy, renowned for its rich artistic heritage and historical significance.
  • E. Chiesa di San Marco
    Chiesa di San Marco is a historic Catholic church in Rovereto, Italy, noted for its religious significance and traditional Trentino architecture.
  • 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_69e0c45e5b8881908ac18fc2f493b114 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee9d0ce8d08190b3233d7117a9b1ca completed April 26, 2026, 11:17 p.m.
Created at: April 16, 2026, 6:27 p.m.