Triple

T12660778
Position Surface form Disambiguated ID Type / Status
Subject University of Lugano E302416 entity
Predicate shortName P43 FINISHED
Object USI
USI is a Swiss public university in Lugano known for its programs in informatics, communication, economics, and architecture.
 E996059 NE FINISHED

How this triple was built (4 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: USI | Statement: [University of Lugano, shortName, USI]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: USI
Context triple: [University of Lugano, shortName, USI]
  • A. USI
    USI is a public university located in Evansville, Indiana, offering a wide range of undergraduate and graduate programs.
  • B. USI
    USI is the abbreviated name for the United States of Indonesia, a short-lived federal state that briefly existed in Southeast Asia after World War II.
  • C. UNIS
    UNIS is a Norwegian higher education and research institution located in Longyearbyen, Svalbard, specializing in Arctic studies and polar research.
  • D. ÚS
    ÚS is the commonly used abbreviation for the Constitutional Court of the Czech Republic, the country's highest authority for constitutional review and protection of fundamental rights.
  • E. SU
    SU is the stock ticker symbol under which Schneider Electric, a global leader in energy management and automation, is traded.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: USI
Triple: [University of Lugano, shortName, USI]
Generated description
USI is a Swiss public university in Lugano known for its programs in informatics, communication, economics, and architecture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: USI
Target entity description: USI is a Swiss public university in Lugano known for its programs in informatics, communication, economics, and architecture.
  • A. USI
    USI is the abbreviated name for the United States of Indonesia, a short-lived federal state that briefly existed in Southeast Asia after World War II.
  • B. USI
    USI is a public university located in Evansville, Indiana, offering a wide range of undergraduate and graduate programs.
  • C. UNIS
    UNIS is a Norwegian higher education and research institution located in Longyearbyen, Svalbard, specializing in Arctic studies and polar research.
  • D. ÚS
    ÚS is the commonly used abbreviation for the Constitutional Court of the Czech Republic, the country's highest authority for constitutional review and protection of fundamental rights.
  • E. SU
    SU is the commonly used abbreviation for Stockholm University, a major public research university in Stockholm, Sweden.
  • F. None of above. chosen

Provenance (5 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9617b07ec8190b714f04ae6654060 completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f66885e44c8190a650301b0e86d0f4 completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f66a602f088190984fa3381b5be944 completed May 2, 2026, 9:19 p.m.
NED2 Entity disambiguation (via description) batch_69f66b18e68881908bf79ab52bcc909e completed May 2, 2026, 9:22 p.m.
Created at: April 9, 2026, 5:19 p.m.