Triple

T1074737
Position Surface form Disambiguated ID Type / Status
Subject Rügen E23809 entity
Predicate hasHarbour P3007 FINISHED
Object Sassnitz harbour E123342 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: Sassnitz harbour | Statement: [Rügen, hasHarbour, Sassnitz harbour]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sassnitz harbour
Context triple: [Rügen, hasHarbour, Sassnitz harbour]
  • A. Sassnitz chosen
    Sassnitz is a port town on the Baltic Sea coast of Germany, located on the island of Rügen and known as a gateway to nearby national parks and chalk cliffs.
  • B. Maienwerder
    Maienwerder is a small island located in the Tegeler See lake in Berlin, Germany, known for its natural setting and limited accessibility.
  • C. Hiddensee
    Hiddensee is a car-free German Baltic Sea island known for its unspoiled nature, sandy beaches, and role as a tranquil holiday destination west of Rügen.
  • D. Island of Usedom
    The Island of Usedom is a Baltic Sea island shared by Germany and Poland, renowned for its long sandy beaches, seaside resorts, and status as a popular holiday destination.
  • E. Perekop Bay
    Perekop Bay is a shallow inlet of the Black Sea located along the northern coast of Crimea, near the Isthmus of Perekop.
  • 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_69a493f1ddf48190a99d54b00e99f8ce completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b92cbfd481909e2f928c1d06ebaa completed March 1, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac599c08f481908b720e2cc7c4a5ef completed March 7, 2026, 5 p.m.
Created at: March 1, 2026, 7:42 p.m.