Triple

T3874802
Position Surface form Disambiguated ID Type / Status
Subject Arnsberg region E92473 entity
Predicate contains P35 FINISHED
Object Unna E101592 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: Unna | Statement: [Arnsberg region, contains, Unna]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unna
Context triple: [Arnsberg region, contains, Unna]
  • A. Unna chosen
    Unna is a town in the German state of North Rhine-Westphalia, known historically as a regional trading center near Dortmund.
  • B. Neilia
    Neilia was an American educator best known as the first wife of Joe Biden, who tragically died in a car accident in 1972 along with their infant daughter.
  • C. Onne
    Onne is a port town in Rivers State, Nigeria, known for its major oil and gas logistics base and deepwater port facilities.
  • D. Fulla
    Fulla is a minor Norse goddess associated with Frigg, known for her long flowing hair, golden headband, and role as a trusted handmaiden and keeper of secrets among the Aesir.
  • E. Ulva
    Ulva is a small, sparsely populated island off the west coast of Scotland, known for its rugged landscapes, wildlife, and historic connections to the Hebrides.
  • 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_69aed967448c819086c4b358d37b25aa completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec59bea08190b1e193f34944a2ee completed March 9, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5124cdf588190b3b83ee8fb29450a completed March 14, 2026, 7:46 a.m.
Created at: March 9, 2026, 3:20 p.m.