Triple

T15773460
Position Surface form Disambiguated ID Type / Status
Subject ADGB E382420 entity
Predicate architecturalPartner P82894 FINISHED
Object Hans Wittwer E968895 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: Hans Wittwer | Statement: [ADGB, architecturalPartner, Hans Wittwer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hans Wittwer
Context triple: [ADGB, architecturalPartner, Hans Wittwer]
  • A. Hans Wittwer chosen
    Hans Wittwer was a Swiss modernist architect and Bauhaus-affiliated designer known for his pioneering functionalist work, including the influential ADGB Trade Union School in Bernau.
  • B. Hans Suter
    Hans Suter is a notable individual who bears the surname Suter, recognized enough to be specifically cited among people with that name.
  • C. Fritz Schlumpf
    Fritz Schlumpf was a Swiss-born French textile industrialist best known for amassing one of the world’s largest and most famous collections of classic automobiles.
  • D. Alfred Wehrli
    Alfred Wehrli was a notable figure significant enough in his community or institution to have Benedetti–Wehrli Stadium named in his honor.
  • E. Heinrich Zurfluh
    Heinrich Zurfluh was a mountaineer known for participating in the first recorded ascent of Dykh-Tau in the Caucasus.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e142df48e8819083a48d3b7b3f7f5d completed April 16, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0139e380bc81908452f6e8666f23ad completed May 11, 2026, 2:07 a.m.
Created at: April 10, 2026, 4:47 a.m.