Triple

T20728615
Position Surface form Disambiguated ID Type / Status
Subject Chioggia E509505 entity
Predicate hasLandmark P105 FINISHED
Object Ponte Vigo 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: Ponte Vigo | Statement: [Chioggia, hasLandmark, Ponte Vigo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ponte Vigo
Context triple: [Chioggia, hasLandmark, Ponte Vigo]
  • A. Ponte Vigo chosen
    Ponte Vigo is a historic stone bridge in the Venetian town of Chioggia, Italy, known for its elegant design and scenic views over the canal.
  • B. Valentré Bridge
    Valentré Bridge is a 14th-century fortified stone arch bridge in Cahors, France, renowned for its medieval military architecture and associated legends.
  • C. Granada Bridge
    Granada Bridge is a vehicular bridge in Ormond Beach, Florida, that spans the Halifax River as part of State Road 40.
  • D. Morell Bridge
    Morell Bridge is a historic pedestrian and cyclist bridge in Melbourne, Australia, known for its distinctive arch design and role in connecting parklands across the Yarra River.
  • E. Bernera Bridge
    Bernera Bridge is a road bridge in the Outer Hebrides of Scotland that connects the island of Great Bernera to the Isle of Lewis.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1eb5d44819082d9fa410e676d91 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:30 p.m.