Triple

T22057029
Position Surface form Disambiguated ID Type / Status
Subject TUM School of Engineering and Design E545045 entity
Predicate hasCampus P116 FINISHED
Object TUM Campus Munich NE NERFINISHED

How this triple was built (3 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: TUM Campus Munich | Statement: [TUM School of Engineering and Design, hasCampus, TUM Campus Munich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TUM Campus Munich
Context triple: [TUM School of Engineering and Design, hasCampus, TUM Campus Munich]
  • A. TUM Campus Garching
    TUM Campus Garching is a major research and teaching hub of the Technical University of Munich, known for its concentration of engineering, natural sciences, and high-tech research facilities north of Munich.
  • B. Munich campus
    The Munich campus is IESE Business School’s German location, offering executive education and MBA-related programs in one of Europe’s major business and innovation hubs.
  • C. TUM Weihenstephan campus
    TUM Weihenstephan campus is the green, research-focused campus of the Technical University of Munich specializing in life sciences, agriculture, and environmental studies.
  • D. Martinsried campus
    Martinsried campus is a major life sciences and biomedical research hub of Ludwig Maximilian University of Munich, located in the Martinsried district near Munich.
  • E. TUM
    TUM is the station code for Tumba railway station in New South Wales, Australia.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: TUM Campus Munich
Target entity description: TUM Campus Munich is a central site of the Technical University of Munich that hosts key facilities, teaching, and research activities of the TUM School of Engineering and Design in the city of Munich.
  • A. TUM Campus Garching
    TUM Campus Garching is a major research and teaching hub of the Technical University of Munich, known for its concentration of engineering, natural sciences, and high-tech research facilities north of Munich.
  • B. Munich campus
    The Munich campus is IESE Business School’s German location, offering executive education and MBA-related programs in one of Europe’s major business and innovation hubs.
  • C. TUM Weihenstephan campus
    TUM Weihenstephan campus is the green, research-focused campus of the Technical University of Munich specializing in life sciences, agriculture, and environmental studies.
  • D. Martinsried campus
    Martinsried campus is a major life sciences and biomedical research hub of Ludwig Maximilian University of Munich, located in the Martinsried district near Munich.
  • E. TUM
    TUM is the station code for Tumba railway station in New South Wales, Australia.
  • F. None of above. chosen

Provenance (2 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_69e11e3377c48190890c17407b9527d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f128588e0081909056ac8251afe935 completed April 28, 2026, 9:36 p.m.
Created at: April 16, 2026, 8:27 p.m.