Triple

T18345772
Position Surface form Disambiguated ID Type / Status
Subject Hilterfingen E439533 entity
Predicate bordersWith P224 FINISHED
Object Heiligenschwendi 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: Heiligenschwendi | Statement: [Hilterfingen, bordersWith, Heiligenschwendi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Heiligenschwendi
Context triple: [Hilterfingen, bordersWith, Heiligenschwendi]
  • A. Heiligenschwendi chosen
    Heiligenschwendi is a small Swiss municipality in the canton of Bern, known for its scenic location above Lake Thun and views of the surrounding Alps.
  • B. Heiligkreuz
    Heiligkreuz is a district of the German city of Trier (Treves), known as a residential area with local churches and community facilities.
  • C. Heiligenkreuz
    Heiligenkreuz is an Austrian village in Lower Austria best known for its historic Cistercian monastery, Heiligenkreuz Abbey, one of the oldest continuously occupied Cistercian monasteries in the world.
  • D. Heretsried
    Heretsried is a small municipality in the Swabian region of Bavaria, Germany, situated within the rural surroundings of the Augsburg district.
  • E. Tannenkirch
    Tannenkirch is a village in the Black Forest region of southwestern Germany that forms one of the districts of the town of Kandern in 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_69d8b9175fec8190af865699b4e64d8c completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e514f3bb888190bdeea4c4d114a43b completed April 19, 2026, 5:46 p.m.
Created at: April 10, 2026, 10:37 a.m.