Triple

T23081371
Position Surface form Disambiguated ID Type / Status
Subject Langenbruck E575481 entity
Predicate borderedBy P224 FINISHED
Object Eptingen 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: Eptingen | Statement: [Langenbruck, borderedBy, Eptingen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eptingen
Context triple: [Langenbruck, borderedBy, Eptingen]
  • A. Eptingen chosen
    Eptingen is a small municipality in the canton of Basel-Landschaft in northwestern Switzerland, known for its rural setting in the Jura hills and its mineral spring.
  • B. Ettingen
    Ettingen is a municipality in the canton of Basel-Landschaft in northwestern Switzerland, situated near the city of Basel.
  • C. Effingen
    Effingen is a small Swiss village and former municipality in the canton of Aargau, known for its rural character and location near the Jura Mountains.
  • D. Engstingen
    Engstingen is a municipality in the state of Baden-Württemberg in southwestern Germany, situated on the Swabian Alb plateau.
  • E. Wechingen
    Wechingen is a small rural municipality in the Bavarian region of southern Germany.
  • 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_69e245be28d48190ad1348d5a73db37d completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f18c67e06881908d24d6267bb49553 completed April 29, 2026, 4:43 a.m.
Created at: April 17, 2026, 3:56 p.m.