Triple

T13537070
Position Surface form Disambiguated ID Type / Status
Subject U5 E323287 entity
Predicate servesDistrict P82 FINISHED
Object Nordend E820013 NE FINISHED

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: [U5, servesDistrict, Nordend]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nordend
Context triple: [U5, servesDistrict, 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 chosen
    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
    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. Denholme
    Denholme is a small town and civil parish in West Yorkshire, England, situated on the eastern edge of the South Pennines.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafbe39948190808062d4eff91841 completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75d9a448c81908fa57a909a9097f7 completed May 3, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:45 p.m.