Triple

T22894564
Position Surface form Disambiguated ID Type / Status
Subject Saint Fosca E568135 entity
Predicate hasShrineIn P27587 FINISHED
Object Torcello 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: Torcello | Statement: [Saint Fosca, hasShrineIn, Torcello]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Torcello
Context triple: [Saint Fosca, hasShrineIn, Torcello]
  • A. Torcello chosen
    Torcello is a sparsely populated island in the Venetian Lagoon known for its early medieval churches and role as one of the earliest centers of settlement in the Venice area.
  • B. Giudecca
    Giudecca is a long, narrow island in the Venetian Lagoon of Italy, known for its residential character, historic churches, and views across the water to central Venice.
  • C. Murano island
    Murano island is a Venetian island in Italy renowned worldwide for its centuries-old tradition of glassmaking and artisan glass workshops.
  • D. Judecca
    Judecca is the innermost and most treacherous region of Hell in Dante Alighieri’s Divine Comedy, where traitors to their benefactors are eternally imprisoned in ice.
  • E. Island of Saint Mark
    Island of Saint Mark is a small, historically significant Adriatic island off the coast of Montenegro, known for its former military use and picturesque natural setting.
  • 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_69e2458c23ec81908fa2570692c6614f completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f17fc83d688190a8ab5ea0aad1e7ec completed April 29, 2026, 3:49 a.m.
Created at: April 17, 2026, 3:40 p.m.