Triple

T8034053
Position Surface form Disambiguated ID Type / Status
Subject Cathedral Island E187058 entity
Predicate hasLandmark P105 FINISHED
Object Tumski Bridge E116911 NE FINISHED

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: Tumski Bridge | Statement: [Cathedral Island, hasLandmark, Tumski Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tumski Bridge
Context triple: [Cathedral Island, hasLandmark, Tumski Bridge]
  • A. Tumski Bridge chosen
    Tumski Bridge is a historic pedestrian bridge in Wrocław, Poland, known for its picturesque views and tradition of lovers attaching padlocks to its railings.
  • B. Solkan Bridge
    Solkan Bridge is a historic stone arch railway bridge in Slovenia, renowned for having the world's longest stone arch span.
  • C. Liteyny Bridge
    Liteyny Bridge is a major steel bascule bridge in Saint Petersburg, Russia, known for carrying traffic across the Neva River and for its role in the city's historic urban landscape.
  • D. Torgovy Bridge
    Torgovy Bridge is a historic pedestrian bridge spanning the Griboyedov Canal in Saint Petersburg, Russia.
  • E. Pevchesky Bridge
    Pevchesky Bridge is a historic pedestrian bridge in Saint Petersburg, Russia, known for spanning the Griboyedov Canal near the city’s central landmarks.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca82ae2d1081909dbfee42b41db419 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3ef3e6848190913c4b1bef506aae completed March 31, 2026, 3:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69ccecc7c7f08190981e00342325a6da completed April 1, 2026, 10 a.m.
Created at: March 30, 2026, 5:22 p.m.