Triple

T14835429
Position Surface form Disambiguated ID Type / Status
Subject Michaelerplatz E348817 entity
Predicate hasLandmark P105 FINISHED
Object Looshaus E777286 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: Looshaus | Statement: [Michaelerplatz, hasLandmark, Looshaus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Looshaus
Context triple: [Michaelerplatz, hasLandmark, Looshaus]
  • A. Looshaus chosen
    Looshaus is a pioneering early modernist building in Vienna, Austria, designed by architect Adolf Loos and renowned for its radical rejection of ornament.
  • B. Ballhaus
    Ballhaus is a German surname most notably associated with a family of prominent cinematographers, including Michael and Florian Ballhaus.
  • C. Gerhaus
    Gerhaus is a small locality or settlement that forms part of the municipality of Rohrau in eastern Austria.
  • D. Mossehaus
    Mossehaus is a landmark early modernist office building in Berlin, Germany, renowned for its dynamic Expressionist façade designed by architect Erich Mendelsohn.
  • E. Trippenhuis
    Trippenhuis is a historic 17th-century canal house in Amsterdam that serves as the headquarters of the Royal Netherlands Academy of Arts and Sciences.
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded076ac9c8190a05cabec5e87d207 completed April 14, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe38a5d8888190821988ad00351d05 completed May 8, 2026, 7:25 p.m.
Created at: April 10, 2026, 1:52 a.m.