Triple

T22435849
Position Surface form Disambiguated ID Type / Status
Subject Zeilsheim E554620 entity
Predicate borderedBy P224 FINISHED
Object Unterliederbach 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: Unterliederbach | Statement: [Zeilsheim, borderedBy, Unterliederbach]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Unterliederbach
Context triple: [Zeilsheim, borderedBy, Unterliederbach]
  • A. Unterliederbach chosen
    Unterliederbach is a district in the west of Frankfurt am Main, Germany, known as a mainly residential area bordering the industrial and commercial hub of Höchst.
  • B. Untergriesbach
    Untergriesbach is a market town in Lower Bavaria, Germany, situated near the Danube River close to the Austrian border.
  • C. Oberaarbach
    Oberaarbach is a mountain stream in the Swiss Alps that feeds into the Hasli-Aare basin.
  • D. Niederbreidenbach
    Niederbreidenbach is a small locality in Germany best known as the birthplace of prominent Nazi official Robert Ley.
  • E. Obergailbach
    Obergailbach is a small commune in northeastern France, located in the Moselle department near the German border.
  • 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15ade60508190b0100d5c2843b920 completed April 29, 2026, 1:11 a.m.
Created at: April 16, 2026, 8:47 p.m.