Triple

T22468933
Position Surface form Disambiguated ID Type / Status
Subject A6 motorway E555436 entity
Predicate connects P390 FINISHED
Object interchange Spiez 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: interchange Spiez | Statement: [A6 motorway, connects, interchange Spiez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: interchange Spiez
Context triple: [A6 motorway, connects, interchange Spiez]
  • A. Spiez chosen
    Spiez is a picturesque Swiss town in the Bernese Oberland, known for its lakeside setting, historic castle, and views of the surrounding Alps.
  • B. Spoerri
    Spoerri is the surname of Daniel Spoerri, a Swiss artist known for his pioneering work in assemblage and the Nouveau Réalisme movement.
  • C. Spiess
    Spiess is a surname of German origin, often borne by individuals in German-speaking countries and their descendants.
  • D. Sieber
    Sieber is the family name of Maria Riva, the actress and author who was the daughter of film legend Marlene Dietrich.
  • E. Sieber
    Sieber is a small river in the German state of Lower Saxony that flows through the Harz Mountains and into the Oder.
  • 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_69e11e52c2048190952dc5df209b9bed completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15bdda62c8190937ac13a4481b4b7 completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:48 p.m.