Triple

T14504739
Position Surface form Disambiguated ID Type / Status
Subject Byala E340235 entity
Predicate hasHeritageSite P923 FINISHED
Object Byala Bridge E346276 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: Byala Bridge | Statement: [Byala, hasHeritageSite, Byala Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Byala Bridge
Context triple: [Byala, hasHeritageSite, Byala Bridge]
  • A. Byala Bridge chosen
    Byala Bridge is a historic 19th-century stone arch bridge in Bulgaria, renowned for its elegant architecture and engineering across the Yantra River.
  • B. Falomo Bridge
    Falomo Bridge is a major road bridge in Lagos, Nigeria, linking the upscale district of Ikoyi with Victoria Island across the Five Cowrie Creek.
  • C. Prachechny Bridge
    Prachechny Bridge is a historic stone bridge in Saint Petersburg, Russia, spanning the Fontanka River near the former imperial laundry buildings.
  • D. Torgovy Bridge
    Torgovy Bridge is a historic pedestrian bridge spanning the Griboyedov Canal in Saint Petersburg, Russia.
  • E. Birzhevoy Bridge
    Birzhevoy Bridge is a bascule bridge in Saint Petersburg, Russia, spanning the Neva River and connecting Vasilyevsky Island with the Petrogradsky side near the historic Stock Exchange.
  • 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_69d822d9c0408190b9a2b3643e58bb4d completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69de94e25a2481908b8394e9a19f3b64 completed April 14, 2026, 7:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd8aaeaf40819087fa0db989813e02 completed May 8, 2026, 7:03 a.m.
Created at: April 10, 2026, 1:21 a.m.