Triple

T6590908
Position Surface form Disambiguated ID Type / Status
Subject River Usk E159352 entity
Predicate hasBridge P386 FINISHED
Object Usk Bridge (Usk) E164255 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: Usk Bridge (Usk) | Statement: [River Usk, hasBridge, Usk Bridge (Usk)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Usk Bridge (Usk)
Context triple: [River Usk, hasBridge, Usk Bridge (Usk)]
  • A. Kandija Bridge
    Kandija Bridge is a historic road bridge spanning the Krka River in Novo Mesto, Slovenia, known as one of the town’s characteristic architectural landmarks.
  • B. 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.
  • C. Pevchesky Bridge
    Pevchesky Bridge is a historic pedestrian bridge in Saint Petersburg, Russia, known for spanning the Moika River near the city’s central cultural and architectural landmarks.
  • D. Ribnica Bridge
    Ribnica Bridge is a historic stone bridge in Podgorica, Montenegro, known as one of the city’s oldest architectural landmarks spanning the Ribnica River.
  • E. Usk Bridge chosen
    Usk Bridge is a historic stone arch bridge spanning the River Usk in the town of Usk, Monmouthshire, Wales.
  • 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_69c688366ce8819083f8883983c0df92 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6aecc969c81909a6e15ebe8dd3f94 completed March 27, 2026, 4:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cbb568508190b9da3475d1620ed5 completed March 27, 2026, 6:25 p.m.
Created at: March 27, 2026, 1:55 p.m.