Triple

T23344862
Position Surface form Disambiguated ID Type / Status
Subject STI E591829 entity
Predicate partOf P40 FINISHED
Object EPFL NE NERFINISHED

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: EPFL | Statement: [STI, partOf, EPFL]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EPFL
Context triple: [STI, partOf, EPFL]
  • A. École polytechnique fédérale de Lausanne chosen
    École polytechnique fédérale de Lausanne is a leading Swiss research university and engineering school known for its cutting-edge work in science, technology, and innovation.
  • B. École polytechnique fédérale de Zurich
    École polytechnique fédérale de Zurich is a leading Swiss public research university in Zurich renowned worldwide for its excellence in science, engineering, and technology.
  • C. Swiss Federal Institutes of Technology
    The Swiss Federal Institutes of Technology are a group of leading Swiss public research universities specializing in science, engineering, and technology, including ETH Zurich and EPFL.
  • D. University of Lausanne
    The University of Lausanne is a major public research university in Lausanne, Switzerland, known for its strengths in law, business, life sciences, and social sciences.
  • E. ETH Zurich
    ETH Zurich is a leading Swiss public research university in Zurich renowned for its excellence in science, engineering, and technology education and innovation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69e25d20e3d08190bcede87673cafb25 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f198358fb8819094c74cfd53cbab44 completed April 29, 2026, 5:33 a.m.
Created at: April 17, 2026, 5:19 p.m.