Triple

T15337735
Position Surface form Disambiguated ID Type / Status
Subject Bruno Taut E366710 entity
Predicate notableWork P4 FINISHED
Object Hufeisensiedlung
Hufeisensiedlung is a pioneering early 20th-century modernist housing estate in Berlin, renowned for its innovative social housing design and distinctive horseshoe-shaped layout.
E1151334 NE FINISHED

How this triple was built (4 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: Hufeisensiedlung | Statement: [Bruno Taut, notableWork, Hufeisensiedlung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hufeisensiedlung
Context triple: [Bruno Taut, notableWork, Hufeisensiedlung]
  • A. Scheibenhof
    Scheibenhof is a locality or district that forms part of the city of Krems an der Donau in Lower Austria.
  • B. Aidhausen
    Aidhausen is a small municipality in the Lower Franconia region of Bavaria, Germany.
  • C. Samenhof
    Samenhof is a surname most notably associated with L. L. Zamenhof, the creator of the constructed international language Esperanto.
  • D. Hunderdorf
    Hunderdorf is a small municipality in the Straubing-Bogen district of Lower Bavaria in southeastern Germany.
  • E. Schönfeldwiese
    Schönfeldwiese is a well-known open meadow in Munich’s Englischer Garten, popular for sunbathing, recreation, and its long tradition of nude bathing.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Hufeisensiedlung
Triple: [Bruno Taut, notableWork, Hufeisensiedlung]
Generated description
Hufeisensiedlung is a pioneering early 20th-century modernist housing estate in Berlin, renowned for its innovative social housing design and distinctive horseshoe-shaped layout.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Hufeisensiedlung
Target entity description: Hufeisensiedlung is a pioneering early 20th-century modernist housing estate in Berlin, renowned for its innovative social housing design and distinctive horseshoe-shaped layout.
  • A. Scheibenhof
    Scheibenhof is a locality or district that forms part of the city of Krems an der Donau in Lower Austria.
  • B. Aidhausen
    Aidhausen is a small municipality in the Lower Franconia region of Bavaria, Germany.
  • C. Samenhof
    Samenhof is a surname most notably associated with L. L. Zamenhof, the creator of the constructed international language Esperanto.
  • D. Hunderdorf
    Hunderdorf is a small municipality in the Straubing-Bogen district of Lower Bavaria in southeastern Germany.
  • E. Schönfeldwiese
    Schönfeldwiese is a well-known open meadow in Munich’s Englischer Garten, popular for sunbathing, recreation, and its long tradition of nude bathing.
  • F. None of above. chosen

Provenance (5 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_69d85a1355608190a6673ddb67231d54 completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e11b22c81908280efe65acd5454 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01f2ee9c819080fce24ed13a07c7 completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff02a62dcc819087eddd2f0b4c29cb completed May 9, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_69ff036153588190ae46fcde257eb3cb completed May 9, 2026, 9:50 a.m.
Created at: April 10, 2026, 3:17 a.m.