Triple

T17372957
Position Surface form Disambiguated ID Type / Status
Subject Lötschberg Tunnel E422361 entity
Predicate connects P390 FINISHED
Object Goppenstein NE NERFINISHED

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: Goppenstein | Statement: [Lötschberg Tunnel, connects, Goppenstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Goppenstein
Context triple: [Lötschberg Tunnel, connects, Goppenstein]
  • A. Goppenstein chosen
    Goppenstein is a small Swiss village in the canton of Valais, best known as a key railway junction and car shuttle station on the Lötschberg route through the Alps.
  • B. Hohnstein
    Hohnstein is a small historic town in Saxony, Germany, known for its medieval castle and scenic location in the Saxon Switzerland region.
  • C. Parthenstein
    Parthenstein is a small municipality in the German state of Saxony, located southeast of Leipzig within its wider metropolitan area.
  • D. Guldenthaler
    Guldenthaler is a historical gold coin variant of the thaler used in parts of Europe.
  • E. Gottenheim
    Gottenheim is a small municipality in southwestern Germany, located near Freiburg im Breisgau in the state of Baden-Württemberg.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a6a9ec881908bfe49413826d37e completed April 19, 2026, 2:14 a.m.
Created at: April 10, 2026, 5:44 a.m.