Triple

T13418253
Position Surface form Disambiguated ID Type / Status
Subject Gisundet strait E313269 entity
Predicate crossedBy P416 FINISHED
Object Gisund Bridge E323766 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: Gisund Bridge | Statement: [Gisundet strait, crossedBy, Gisund Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gisund Bridge
Context triple: [Gisundet strait, crossedBy, Gisund Bridge]
  • A. Gisund Bridge chosen
    Gisund Bridge is a cantilever road bridge in northern Norway that spans the Gisundet strait, linking the island of Senja to the mainland.
  • B. Yanggak Bridge
    Yanggak Bridge is a major road bridge in Pyongyang, North Korea, that spans the Taedong River and provides access to Yanggak Island.
  • C. Chonhar Bridge
    The Chonhar Bridge is a strategically important road and rail bridge connecting mainland Ukraine with the Crimean Peninsula across the Syvash.
  • D. Rombak Bridge
    Rombak Bridge is a railway bridge in northern Norway that carries the Ofoten Line across the Rombaken fjord near Narvik.
  • E. Sennoy Bridge
    Sennoy Bridge is a pedestrian bridge in Saint Petersburg, Russia, spanning the Griboyedov Canal near the historic Sennaya Square.
  • 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_69d806ad0c44819088833ae1ec9e9690 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dbaeb8416c8190a00dde0917c26f51 completed April 12, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75475d7648190b050e44a5312d13d completed May 3, 2026, 1:58 p.m.
Created at: April 9, 2026, 9:39 p.m.