Triple

T21002302
Position Surface form Disambiguated ID Type / Status
Subject Tumba station E517323 entity
Predicate hasStationCode P1289 FINISHED
Object TUM 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 | Statement: [Tumba station, hasStationCode, TUM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: TUM
Context triple: [Tumba station, hasStationCode, TUM]
  • A. TUMSAT
    TUMSAT is a Japanese national university specializing in marine science, fisheries, and related technologies, based in Tokyo.
  • B. TUM School of Engineering and Design
    TUM School of Engineering and Design is a major school of the Technical University of Munich that integrates engineering, design, and technology-focused disciplines under one interdisciplinary umbrella.
  • C. TUM School of Social Sciences and Technology
    The TUM School of Social Sciences and Technology is a faculty of the Technical University of Munich that focuses on the intersection of social sciences, education, and technology in research and teaching.
  • D. 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.
  • E. Ulm University
    Ulm University is a public research university in Ulm, Germany, known for its strong programs in natural sciences, medicine, engineering, and economics.
  • 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
Target entity description: TUM is the station code for Tumba railway station in New South Wales, Australia.
  • A. TUMSAT
    TUMSAT is a Japanese national university specializing in marine science, fisheries, and related technologies, based in Tokyo.
  • B. TUM School of Engineering and Design
    TUM School of Engineering and Design is a major school of the Technical University of Munich that integrates engineering, design, and technology-focused disciplines under one interdisciplinary umbrella.
  • C. TUM School of Social Sciences and Technology
    The TUM School of Social Sciences and Technology is a faculty of the Technical University of Munich that focuses on the intersection of social sciences, education, and technology in research and teaching.
  • D. 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.
  • E. Ulm University
    Ulm University is a public research university in Ulm, Germany, known for its strong programs in natural sciences, medicine, engineering, and economics.
  • 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_69e0b50192308190a284fcc89dd23a49 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc38b8688190860fba1b58e1b3e6 completed April 21, 2026, 4:25 a.m.
Created at: April 16, 2026, 1:52 p.m.