Triple

T16381254
Position Surface form Disambiguated ID Type / Status
Subject Soest district E397811 entity
Predicate containsAdministrativeTerritorialEntity P747 FINISHED
Object Welver E990686 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: Welver | Statement: [Soest district, containsAdministrativeTerritorialEntity, Welver]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Welver
Context triple: [Soest district, containsAdministrativeTerritorialEntity, Welver]
  • A. Welver chosen
    Welver is a municipality in the German state of North Rhine-Westphalia, situated in the Soest district within the historic region of Westphalia.
  • B. Welun
    Welun is the German name for the Polish town of Wieluń, known for being one of the first places bombed at the start of World War II.
  • C. Welk
    Welk is a surname most famously associated with American bandleader and television host Lawrence Welk.
  • D. Vere
    Vere is the given name of Vere Gordon Childe, a prominent Australian archaeologist known for his influential theories on prehistoric societies and social evolution.
  • E. Veeweyde
    Veeweyde is a neighborhood-level district within the Brussels municipality of Anderlecht, known primarily as a residential area served by the Veeweyde metro station.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e319dd0e0c8190812bde6a2f7d9644 completed April 18, 2026, 5:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0035689ef08190ba980a359498ca56 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.