Triple

T12337531

Position	Surface form	Disambiguated ID	Type / Status
Subject	Faculty of Engineering, University of New South Wales	`E294128`	entity
Predicate	hasDepartment	`P35`	FINISHED
Object	School of Chemical Engineering, UNSW The School of Chemical Engineering at UNSW is a leading academic unit specializing in education and research in chemical, process, and related engineering disciplines within the university’s Faculty of Engineering.	`E978494`	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: School of Chemical Engineering, UNSW | Statement: [Faculty of Engineering, University of New South Wales, hasDepartment, School of Chemical Engineering, UNSW]

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

Target entity: School of Chemical Engineering, UNSW
Context triple: [Faculty of Engineering, University of New South Wales, hasDepartment, School of Chemical Engineering, UNSW]

A. School of Chemical Engineering
The School of Chemical Engineering is an academic unit specializing in chemical engineering education and research within Hanoi University of Science and Technology.
B. School of Chemical Engineering
The School of Chemical Engineering is an academic unit of Nanjing University of Science and Technology specializing in education and research in chemical engineering and related disciplines.
C. School of Chemical Engineering
The School of Chemical Engineering at the University of Tehran is a leading academic and research institution in Iran specializing in chemical engineering education, innovation, and industry collaboration.
D. School of Chemical Engineering
The School of Chemical Engineering is a specialized academic unit of East China University of Science and Technology focused on education and research in chemical engineering and related disciplines.
E. School of Chemical Engineering
The School of Chemical Engineering is an academic unit of the National Technical University of Athens specializing in education and research in chemical engineering and related fields.
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: School of Chemical Engineering, UNSW
Triple: [Faculty of Engineering, University of New South Wales, hasDepartment, School of Chemical Engineering, UNSW]

Generated description

The School of Chemical Engineering at UNSW is a leading academic unit specializing in education and research in chemical, process, and related engineering disciplines within the university’s Faculty of Engineering.

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

Target entity: School of Chemical Engineering, UNSW
Target entity description: The School of Chemical Engineering at UNSW is a leading academic unit specializing in education and research in chemical, process, and related engineering disciplines within the university’s Faculty of Engineering.

A. School of Chemical Engineering
The School of Chemical Engineering is a specialized academic unit of East China University of Science and Technology focused on education and research in chemical engineering and related disciplines.
B. School of Chemical Engineering
The School of Chemical Engineering is an academic unit specializing in chemical engineering education and research within Hanoi University of Science and Technology.
C. School of Chemical Engineering
The School of Chemical Engineering at the University of Tehran is a leading academic and research institution in Iran specializing in chemical engineering education, innovation, and industry collaboration.
D. School of Chemical Engineering
The School of Chemical Engineering is an academic unit of the National Technical University of Athens specializing in education and research in chemical engineering and related fields.
E. School of Chemical Engineering
The School of Chemical Engineering is an academic unit of Nanjing University of Science and Technology specializing in education and research in chemical engineering and related disciplines.
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_69d6ab6ae0dc8190b1522a9c1c55c114`	completed	April 8, 2026, 7:24 p.m.
NER	Named-entity recognition	`batch_69d93f678698819091462b44ff3435f6`	completed	April 10, 2026, 6:20 p.m.
NED1	Entity disambiguation (via context triple)	`batch_69f62aa5f21c8190bcb32a078a2f7ebb`	completed	May 2, 2026, 4:47 p.m.
NEDg	Description generation	`batch_69f62c54e6b08190bdae0ec35cc1c48d`	completed	May 2, 2026, 4:54 p.m.
NED2	Entity disambiguation (via description)	`batch_69f62d13237881908b7c2dca173e20cf`	completed	May 2, 2026, 4:57 p.m.

Created at: April 8, 2026, 9:53 p.m.