Triple

T21415304
Position Surface form Disambiguated ID Type / Status
Subject Swinemünde area E528285 entity
Predicate historicalMainTown P143877 FINISHED
Object Swinemünde NE NERFINISHED

How this triple was built (3 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: Swinemünde | Statement: [Swinemünde area, historicalMainTown, Swinemünde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swinemünde
Context triple: [Swinemünde area, historicalMainTown, Swinemünde]
  • A. Swinemünde chosen
    Swinemünde is a historic Baltic Sea port town, now known as Świnoujście in Poland, situated on the islands of Usedom and Wolin near the German border.
  • B. Stolpmünde
    Stolpmünde is the former German name for the Baltic Sea port town now known as Ustka in northern Poland.
  • C. Ueckermünde
    Ueckermünde is a small historic port town in northeastern Germany on the Szczecin Lagoon, known for its maritime heritage and access to the Baltic Sea.
  • D. Schwarmstedt
    Schwarmstedt is a municipality in Lower Saxony, Germany, situated in the Heidekreis district along the River Aller.
  • E. Maienwerder
    Maienwerder is a small island located in the Tegeler See lake in Berlin, Germany, known for its natural setting and limited accessibility.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: historicalMainTown
Context triple: [Swinemünde area, historicalMainTown, Swinemünde]
  • A. historicalTownName
    Indicates that the object is a former or historical name by which the town (subject) was previously known.
  • B. containsHistoricTown
    Indicates that one entity geographically includes or encompasses a town that has recognized historical significance.
  • C. historicalTownshipOf
    Indicates that one entity was formerly a township encompassing or governing the other entity during a past historical period.
  • D. governsHistoricTown
    Indicates that one entity exercises official governing authority over a town that is recognized as historically significant.
  • E. focusCityHistory
    Indicates that there is a historical or context-defining relationship between a focal city and its past events, developments, or status.
  • F. None of above. chosen

Provenance (4 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_69e0c454c248819093425d1099101c09 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69ee62d16bfc8190a1c08dd9d0c80e02 completed April 26, 2026, 7:09 p.m.
PD Predicate disambiguation batch_69e61633f8208190a2a849457c4e4198 completed April 20, 2026, 12:04 p.m.
PDg Predicate description generation batch_69e6190163448190a2404b396215c686 completed April 20, 2026, 12:16 p.m.
Created at: April 16, 2026, 5:45 p.m.