Triple

T1092681
Position Surface form Disambiguated ID Type / Status
Subject École polytechnique fédérale de Lausanne E24200 entity
Predicate sisterInstitution P3457 FINISHED
Object ETH Zurich E4310 NE FINISHED

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: ETH Zurich | Statement: [École polytechnique fédérale de Lausanne, sisterInstitution, ETH Zurich]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ETH Zurich
Context triple: [École polytechnique fédérale de Lausanne, sisterInstitution, ETH Zurich]
  • A. ETH Zurich chosen
    ETH Zurich is a leading Swiss public research university in Zurich renowned for its excellence in science, engineering, and technology education 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. École polytechnique fédérale de Lausanne
    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.
  • D. University of Zurich
    The University of Zurich is a major public research university in Switzerland renowned for its contributions to science and scholarship, including being one of the institutions where Albert Einstein taught.
  • E. Swiss Federal Institutes of Technology Domain
    The Swiss Federal Institutes of Technology Domain is a Swiss government-controlled network of leading science and technology institutions, including ETH Zurich and EPFL, focused on advanced research, education, and innovation.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: sisterInstitution
Context triple: [École polytechnique fédérale de Lausanne, sisterInstitution, ETH Zurich]
  • A. relatedInstitution
    Indicates that there is an institutional connection or association between two entities, such as affiliation, partnership, or organizational linkage.
  • B. associatedInstitution
    Indicates that an entity has a formal connection or affiliation with a particular institution.
  • C. hasSisterOrganization chosen
    Indicates that one organization is related to another as a sister organization, typically sharing a common parent, affiliation, or parallel status within the same overarching structure.
  • D. sisterCollege
    Indicates a formal partnership or affiliation between two colleges, typically for mutual support, exchange, or shared programs.
  • E. sponsoringInstitution
    Indicates that an institution provides financial or organizational support to enable or underwrite an activity, project, event, or entity.
  • F. None of above.

Provenance (4 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_69a4940542308190ac2a0b1f730b7cfc completed March 1, 2026, 7:31 p.m.
NER Named-entity recognition batch_69a4b99bd06c8190bce1d77b0337b07c completed March 1, 2026, 10:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69acacaafe5c8190968cd74e59ceaa53 completed March 7, 2026, 10:54 p.m.
PD Predicate disambiguation batch_69a4b743175481908f3967e589717c55 completed March 1, 2026, 10:01 p.m.
Created at: March 1, 2026, 7:42 p.m.