Triple

T5332482
Position Surface form Disambiguated ID Type / Status
Subject Sellin E123341 entity
Predicate hasAttraction P105 FINISHED
Object Sellin Pier E511700 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: Sellin Pier | Statement: [Sellin, hasAttraction, Sellin Pier]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sellin Pier
Context triple: [Sellin, hasAttraction, Sellin Pier]
  • A. Sellin Pier chosen
    Sellin Pier is a historic seaside pier and popular tourist attraction on the island of Rügen in Germany, known for its distinctive pavilion and scenic Baltic Sea views.
  • B. Mount Hope
    Mount Hope is a prominent hill in Rochester, New York, known for giving its name and terrain to the historic Mount Hope Cemetery and surrounding neighborhood.
  • C. Mount Hope
    Mount Hope is a small city in southern West Virginia known historically for its roots in the coal mining industry and its location near outdoor recreation areas.
  • D. Town Pier
    Town Pier is a historic riverside pier in Gravesend, England, serving as a local landmark and passenger landing stage on the River Thames.
  • E. Blackrock Pier
    Blackrock Pier is a small coastal pier and local landmark in the village of Blackrock in County Cork, Ireland, used for leisure, fishing, and waterfront access.
  • 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_69bd46477f9081909d242a327d749466 completed March 20, 2026, 1:06 p.m.
NER Named-entity recognition batch_69bd85aab0308190990626cbc9da3e21 completed March 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21bebea0819083e6deae67f3e834 completed March 21, 2026, 10:54 p.m.
Created at: March 20, 2026, 2 p.m.