Triple

T20975354
Position Surface form Disambiguated ID Type / Status
Subject Accademia Bridge E516610 entity
Predicate connectsDistrict P2564 FINISHED
Object San Marco 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 | Statement: [Accademia Bridge, connectsDistrict, San Marco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: San Marco
Context triple: [Accademia Bridge, connectsDistrict, San Marco]
  • A. San Marco
    San Marco is a locality or district within the Italian town of Minturno, known as one of its constituent settlements.
  • B. San Marco chosen
    San Marco is Venice’s historic central district, renowned for its iconic St. Mark’s Square, basilica, and proximity to major landmarks along the Grand Canal.
  • C. San Marco dei Cavoti
    San Marco dei Cavoti is a small hill town in southern Italy known for its traditional torrone (nougat) production and historic medieval center.
  • D. San Marco church
    San Marco church is a historic Christian church located in the Sicilian city of Enna, Italy.
  • E. Santa Maria sopra Minerva
    Santa Maria sopra Minerva is a prominent Gothic-style Roman Catholic church in central Rome, renowned for its rich artistic heritage and as the burial site of several notable historical figures.
  • 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_69e0b4fee5ac8190875fa9ceba1a5e5e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fba3df2081908c1db5f8610ba43d completed April 21, 2026, 4:23 a.m.
Created at: April 16, 2026, 1:46 p.m.