Triple

T14331867
Position Surface form Disambiguated ID Type / Status
Subject Herne E355366 entity
Predicate hasTwinTown P919 FINISHED
Object Konin E176381 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: Konin | Statement: [Herne, hasTwinTown, Konin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Konin
Context triple: [Herne, hasTwinTown, Konin]
  • A. Konin chosen
    Konin is an industrial city in central Poland known for its power plants and location along the Warta River.
  • B. Kuneē
    Kuneē is the mythological helmet worn by Hades that grants its wearer invisibility in Greek mythology.
  • C. Koubia
    Koubia is a town in the Middle Guinea region of Guinea that serves as an important local administrative and commercial center.
  • D. Karasuwa
    Karasuwa is a local government area in northeastern Nigeria known for its predominantly rural communities and agricultural activities within Yobe State.
  • E. Rijsoord
    Rijsoord is a village in the Dutch province of South Holland, known as the site where the Netherlands formally surrendered to Germany in May 1940.
  • 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_69d8278fa2108190bc0d0e7939c1eb03 completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de8c1fb87c81908412c2953243c8e3 completed April 14, 2026, 6:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd46943dac819092f5935d9d312949 completed May 8, 2026, 2:12 a.m.
Created at: April 10, 2026, 1:13 a.m.