Triple

T19420156
Position Surface form Disambiguated ID Type / Status
Subject Causeway Bridge E485829 entity
Predicate hasName P744 FINISHED
Object Causeway Bridge 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: Causeway Bridge | Statement: [Causeway Bridge, hasName, Causeway Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Causeway Bridge
Context triple: [Causeway Bridge, hasName, Causeway Bridge]
  • A. Causeway Bridge chosen
    Causeway Bridge is a major road bridge in Perth, Western Australia, carrying traffic across the Swan River between the city centre and the eastern suburbs.
  • B. Causeway Bridge
    Causeway Bridge is a major road bridge spanning Simpson Bay Lagoon on the Caribbean island of Sint Maarten, improving traffic flow between key parts of the island.
  • C. Long Bridge
    Long Bridge is a notable bridge that serves as a key nearby landmark to Prague’s historic Green Gate.
  • D. Long Bridge
    Long Bridge is a historic multi-arched stone bridge spanning the River Taw in Barnstaple, Devon, England.
  • E. Long Bridge
    Long Bridge is the massive, ancient stone bridge in the city of Volantis in the world of A Song of Ice and Fire, lined with buildings, markets, and temples that make it a bustling hub of commerce and life.
  • 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63213b6ec8190b89982b554a0f6e7 completed April 20, 2026, 2:02 p.m.
Created at: April 10, 2026, 1:37 p.m.