Triple

T5568841
Position Surface form Disambiguated ID Type / Status
Subject Petrolina E145945 entity
Predicate hasHigherEducationInstitution P113 FINISHED
Object Universidade Federal do Vale do São Francisco
A Brazilian federal public university located in the São Francisco Valley region, known for serving the semi-arid Northeast with programs in areas such as agrarian sciences, health, and engineering.
E534365 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: Universidade Federal do Vale do São Francisco | Statement: [Petrolina, hasHigherEducationInstitution, Universidade Federal do Vale do São Francisco]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Universidade Federal do Vale do São Francisco
Context triple: [Petrolina, hasHigherEducationInstitution, Universidade Federal do Vale do São Francisco]
  • A. Federal University of Western Pará
    The Federal University of Western Pará is a Brazilian public higher education and research institution located in the Amazonian city of Santarém, serving as a key center for regional development and environmental studies.
  • B. São Paulo State University
    São Paulo State University is a major Brazilian public university system known for its multiple campuses across the state of São Paulo and its strong emphasis on research and higher education.
  • C. Universidade Católica de Santos
    Universidade Católica de Santos is a private Catholic university in the coastal city of Santos, Brazil, known for its programs in areas such as law, health sciences, and humanities.
  • D. University of Recife
    The University of Recife was a Brazilian higher education institution in Pernambuco known for its role in mid-20th-century academic and intellectual life, particularly in the social and human sciences.
  • E. Federal University of Mato Grosso
    The Federal University of Mato Grosso is a major Brazilian public university and research institution headquartered in the state of Mato Grosso.
  • 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: Universidade Federal do Vale do São Francisco
Triple: [Petrolina, hasHigherEducationInstitution, Universidade Federal do Vale do São Francisco]
Generated description
A Brazilian federal public university located in the São Francisco Valley region, known for serving the semi-arid Northeast with programs in areas such as agrarian sciences, health, and engineering.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Universidade Federal do Vale do São Francisco
Target entity description: A Brazilian federal public university located in the São Francisco Valley region, known for serving the semi-arid Northeast with programs in areas such as agrarian sciences, health, and engineering.
  • A. Federal University of Western Pará
    The Federal University of Western Pará is a Brazilian public higher education and research institution located in the Amazonian city of Santarém, serving as a key center for regional development and environmental studies.
  • B. São Paulo State University
    São Paulo State University is a major Brazilian public university system known for its multiple campuses across the state of São Paulo and its strong emphasis on research and higher education.
  • C. Universidade Católica de Santos
    Universidade Católica de Santos is a private Catholic university in the coastal city of Santos, Brazil, known for its programs in areas such as law, health sciences, and humanities.
  • D. University of Recife
    The University of Recife was a Brazilian higher education institution in Pernambuco known for its role in mid-20th-century academic and intellectual life, particularly in the social and human sciences.
  • E. Federal University of Mato Grosso
    The Federal University of Mato Grosso is a major Brazilian public university and research institution headquartered in the state of Mato Grosso.
  • 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_69c008fdae24819081aa002ad99cd966 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c0203789688190a0bab723186214ad completed March 22, 2026, 5 p.m.
NED1 Entity disambiguation (via context triple) batch_69c04d177d18819090018371d22c66a3 completed March 22, 2026, 8:12 p.m.
NEDg Description generation batch_69c04e868cc48190bdb245ba52b9b938 completed March 22, 2026, 8:18 p.m.
NED2 Entity disambiguation (via description) batch_69c04f0de68c8190817b525f2d8ef327 completed March 22, 2026, 8:20 p.m.
Created at: March 22, 2026, 3:36 p.m.