Triple

T1720307

Position	Surface form	Disambiguated ID	Type / Status
Subject	Helsinki University of Technology	`E37373`	entity
Predicate	hasFaculty	`P141`	FINISHED
Object	Faculty of Engineering and Architecture The Faculty of Engineering and Architecture is an academic division of Helsinki University of Technology specializing in engineering and architectural education and research.	`E202993`	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 Engineering and Architecture | Statement: [Helsinki University of Technology, hasFaculty, Faculty of Engineering and Architecture]

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Faculty of Engineering and Architecture
Context triple: [Helsinki University of Technology, hasFaculty, Faculty of Engineering and Architecture]

A. Faculty of Engineering and Architecture
The Faculty of Engineering and Architecture is a major academic division of the American University of Beirut offering undergraduate and graduate programs in engineering and architectural disciplines.
B. Faculty of Engineering and Architecture
The Faculty of Engineering and Architecture is a major academic division of Ghent University in Belgium, offering a wide range of engineering and architectural programs and conducting research in technology and the built environment.
C. Faculty of Engineering and Architectural Science
The Faculty of Engineering and Architectural Science is a major academic division of Toronto Metropolitan University offering programs in engineering, architecture, and related applied sciences.
D. School of Engineering and Architecture
The School of Engineering and Architecture is a faculty of the University of Bologna that offers interdisciplinary education and research in engineering disciplines and architectural studies.
E. Faculty of Engineering
The Faculty of Engineering at the University of Tokyo is a leading academic division renowned for its cutting-edge research and education in engineering and technology in Japan and worldwide.
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 Engineering and Architecture
Triple: [Helsinki University of Technology, hasFaculty, Faculty of Engineering and Architecture]

Generated description

The Faculty of Engineering and Architecture is an academic division of Helsinki University of Technology specializing in engineering and architectural education and research.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Faculty of Engineering and Architecture
Target entity description: The Faculty of Engineering and Architecture is an academic division of Helsinki University of Technology specializing in engineering and architectural education and research.

A. Faculty of Engineering and Architecture
The Faculty of Engineering and Architecture is a major academic division of Ghent University in Belgium, offering a wide range of engineering and architectural programs and conducting research in technology and the built environment.
B. Faculty of Engineering and Architecture
The Faculty of Engineering and Architecture is a major academic division of the American University of Beirut offering undergraduate and graduate programs in engineering and architectural disciplines.
C. Faculty of Engineering and Architectural Science
The Faculty of Engineering and Architectural Science is a major academic division of Toronto Metropolitan University offering programs in engineering, architecture, and related applied sciences.
D. School of Engineering and Architecture
The School of Engineering and Architecture is a faculty of the University of Bologna that offers interdisciplinary education and research in engineering disciplines and architectural studies.
E. Faculty of Engineering
The Faculty of Engineering is a leading academic unit of the Pontifical Catholic University of Chile, recognized for its engineering education, research, and technological innovation.
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_69a8861912dc8190931af43b4b9158a7`	completed	March 4, 2026, 7:20 p.m.
NER	Named-entity recognition	`batch_69aa63558d7c8190830cb8ee2e4a8932`	completed	March 6, 2026, 5:17 a.m.
NED1	Entity disambiguation (via context triple)	`batch_69adbf498848819085cd7faffd86cd77`	completed	March 8, 2026, 6:26 p.m.
NEDg	Description generation	`batch_69adbff135188190908058a2e2d41a1e`	completed	March 8, 2026, 6:29 p.m.
NED2	Entity disambiguation (via description)	`batch_69adc0832cd881909702f380412702d5`	completed	March 8, 2026, 6:31 p.m.

Created at: March 4, 2026, 7:30 p.m.