Triple

T22476612
Position Surface form Disambiguated ID Type / Status
Subject Westend (Frankfurt am Main) E555646 entity
Predicate adjacentTo P224 FINISHED
Object Nordend 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: Nordend | Statement: [Westend (Frankfurt am Main), adjacentTo, Nordend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nordend
Context triple: [Westend (Frankfurt am Main), adjacentTo, Nordend]
  • A. Nordend
    Nordend is one of the main summits of the Monte Rosa massif in the Pennine Alps, known as one of the highest peaks in Switzerland.
  • B. Nordend
    Nordend is a district of the German town of Eberswalde in the state of Brandenburg.
  • C. Northend
    Northend is a small hamlet within the parish of Turville in Buckinghamshire, England, known for its rural character and traditional English countryside setting.
  • D. Nordend-West chosen
    Nordend-West is a central residential district of Frankfurt am Main, Germany, known for its historic architecture, lively urban atmosphere, and proximity to the city center.
  • E. Glenfield
    Glenfield is a village and civil parish in Leicestershire, England, situated just northwest of Leicester.
  • 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_69f15be48cec8190baff90f8566a85d0 completed April 29, 2026, 1:16 a.m.
Created at: April 16, 2026, 8:49 p.m.