Triple

T14750690
Position Surface form Disambiguated ID Type / Status
Subject San Matteo Polyclinic E346592 entity
Predicate hasCollaboration P10645 FINISHED
Object University of Pavia Faculty of Medicine and Surgery
The University of Pavia Faculty of Medicine and Surgery is a historic Italian medical school renowned for its clinical training, biomedical research, and integration with major teaching hospitals.
E1117362 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: University of Pavia Faculty of Medicine and Surgery | Statement: [San Matteo Polyclinic, hasCollaboration, University of Pavia Faculty of Medicine and Surgery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: University of Pavia Faculty of Medicine and Surgery
Context triple: [San Matteo Polyclinic, hasCollaboration, University of Pavia Faculty of Medicine and Surgery]
  • A. University Hospital of Trieste
    The University Hospital of Trieste is a major teaching and research hospital in Trieste, Italy, serving as the primary clinical center for the University of Trieste’s medical faculty.
  • B. UST Faculty of Medicine and Surgery
    UST Faculty of Medicine and Surgery is the medical school of the University of Santo Tomas in the Philippines, recognized as one of the country’s oldest and most prestigious institutions for medical education and training.
  • C. Careggi University Hospital
    Careggi University Hospital is a major teaching and research hospital in Florence, Italy, affiliated with the University of Florence and serving as one of the country’s principal tertiary care centers.
  • D. University of Milano-Bicocca
    The University of Milano-Bicocca is a public research university in Milan, Italy, known for its strong programs in economics, science, and law.
  • E. University of Parma
    The University of Parma is one of Italy’s oldest universities, a historic higher education institution located in the city of Parma in the Emilia-Romagna region.
  • 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: University of Pavia Faculty of Medicine and Surgery
Triple: [San Matteo Polyclinic, hasCollaboration, University of Pavia Faculty of Medicine and Surgery]
Generated description
The University of Pavia Faculty of Medicine and Surgery is a historic Italian medical school renowned for its clinical training, biomedical research, and integration with major teaching hospitals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: University of Pavia Faculty of Medicine and Surgery
Target entity description: The University of Pavia Faculty of Medicine and Surgery is a historic Italian medical school renowned for its clinical training, biomedical research, and integration with major teaching hospitals.
  • A. University Hospital of Trieste
    The University Hospital of Trieste is a major teaching and research hospital in Trieste, Italy, serving as the primary clinical center for the University of Trieste’s medical faculty.
  • B. UST Faculty of Medicine and Surgery
    UST Faculty of Medicine and Surgery is the medical school of the University of Santo Tomas in the Philippines, recognized as one of the country’s oldest and most prestigious institutions for medical education and training.
  • C. Careggi University Hospital
    Careggi University Hospital is a major teaching and research hospital in Florence, Italy, affiliated with the University of Florence and serving as one of the country’s principal tertiary care centers.
  • D. University of Milano-Bicocca
    The University of Milano-Bicocca is a public research university in Milan, Italy, known for its strong programs in economics, science, and law.
  • E. University of Parma
    The University of Parma is one of Italy’s oldest universities, a historic higher education institution located in the city of Parma in the Emilia-Romagna region.
  • 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_69d822e6f1c88190bc494d491a907114 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec7d2e1748190b16ede681fe52872 completed April 14, 2026, 11:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69fdfb9a56a08190b6a178cd930a072d completed May 8, 2026, 3:04 p.m.
NEDg Description generation batch_69fdfde8ed30819083600cdac241675e completed May 8, 2026, 3:14 p.m.
NED2 Entity disambiguation (via description) batch_69fdfe969a6081908f4ebec0f6538811 completed May 8, 2026, 3:17 p.m.
Created at: April 10, 2026, 1:30 a.m.