Triple

T8601414
Position Surface form Disambiguated ID Type / Status
Subject Dnipro University of Technology E203682 entity
Predicate hasFaculty P141 FINISHED
Object Faculty of Information Technologies
The Faculty of Information Technologies is an academic division of Dnipro University of Technology specializing in education and research in computer science and related IT disciplines.
E744809 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: Faculty of Information Technologies | Statement: [Dnipro University of Technology, hasFaculty, Faculty of Information Technologies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Faculty of Information Technologies
Context triple: [Dnipro University of Technology, hasFaculty, Faculty of Information Technologies]
  • A. Faculty of Information Technology
    The Faculty of Information Technology is a specialized computer science and IT faculty of the Czech Technical University in Prague, focusing on education and research in informatics, software engineering, and related technologies.
  • B. Faculty of Information Technology
    The Faculty of Information Technology is an academic division of Taras Shevchenko National University of Kyiv specializing in computer science, software engineering, and related IT disciplines.
  • C. Faculty of Information Technology
    The Faculty of Information Technology at the University of Jordan is an academic unit specializing in education and research in computing, software, and information systems.
  • D. Faculty of Information Technology
    The Faculty of Information Technology is an academic division of the Libyan International Medical University specializing in education and research in computing and information systems.
  • E. Faculty of Information Technology
    The Faculty of Information Technology is Monash University's dedicated academic division for teaching and research in computing, software, data science, and related information technologies.
  • 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: Faculty of Information Technologies
Triple: [Dnipro University of Technology, hasFaculty, Faculty of Information Technologies]
Generated description
The Faculty of Information Technologies is an academic division of Dnipro University of Technology specializing in education and research in computer science and related IT disciplines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Faculty of Information Technologies
Target entity description: The Faculty of Information Technologies is an academic division of Dnipro University of Technology specializing in education and research in computer science and related IT disciplines.
  • A. Faculty of Information Technology
    The Faculty of Information Technology at the University of Jordan is an academic unit specializing in education and research in computing, software, and information systems.
  • B. Faculty of Information Technology
    The Faculty of Information Technology is a specialized computer science and IT faculty of the Czech Technical University in Prague, focusing on education and research in informatics, software engineering, and related technologies.
  • C. Faculty of Information Technology
    The Faculty of Information Technology is an academic division of Taras Shevchenko National University of Kyiv specializing in computer science, software engineering, and related IT disciplines.
  • D. Faculty of Information Technology
    The Faculty of Information Technology is an academic division of the Libyan International Medical University specializing in education and research in computing and information systems.
  • E. Faculty of Information Technology
    The Faculty of Information Technology is Monash University's dedicated academic division for teaching and research in computing, software, data science, and related information technologies.
  • 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_69ca832b56948190ba751cec255308f1 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc46d8ff408190acc7cd8dc99b2689 completed March 31, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea8f13f7081908317c1b2d87a51b2 completed April 2, 2026, 5:35 p.m.
NEDg Description generation batch_69cea9d0dad0819095134f6f8cafb4c0 completed April 2, 2026, 5:39 p.m.
NED2 Entity disambiguation (via description) batch_69ceaa7025388190a3f17aca46d4858e completed April 2, 2026, 5:42 p.m.
Created at: March 30, 2026, 6:24 p.m.