Triple

T4387167
Position Surface form Disambiguated ID Type / Status
Subject Macclesfield E99270 entity
Predicate hasTwinTown P919 FINISHED
Object Eckernförde E228983 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: Eckernförde | Statement: [Macclesfield, hasTwinTown, Eckernförde]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eckernförde
Context triple: [Macclesfield, hasTwinTown, Eckernförde]
  • A. Eckernförde chosen
    Eckernförde is a coastal town in northern Germany known for its Baltic Sea beaches, historic harbor, and maritime tourism.
  • B. Svinesund
    Svinesund is a strait forming part of the border between Norway and Sweden, best known for its bridges and role as a major road crossing between the two countries.
  • C. Güstrow
    Güstrow is a historic town in northern Germany known for its Renaissance castle, brick Gothic cathedral, and association with sculptor Ernst Barlach.
  • D. Itzehoe
    Itzehoe is a historic town in northern Germany known for its medieval origins and role as a regional center in the state of Schleswig-Holstein.
  • E. Rudkøbing
    Rudkøbing is a small historic town on the Danish island of Langeland, known for its well-preserved old streets and as the birthplace of physicist Hans Christian Ørsted.
  • 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_69b3454f739481909ff6c28331f0c0b9 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b352804be88190ab188ac0dde1ac1e completed March 12, 2026, 11:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e52a0488819081fe724d592d8fdf completed March 14, 2026, 10:46 p.m.
Created at: March 12, 2026, 11:19 p.m.