Triple

T2915207

Position	Surface form	Disambiguated ID	Type / Status
Subject	College of Engineering (University of Michigan)	`E63788`	entity
Predicate	hasUnit	`P35`	FINISHED
Object	Department of Mechanical Engineering (University of Michigan) The Department of Mechanical Engineering at the University of Michigan is a leading academic and research department known for its work in areas such as automotive engineering, robotics, energy systems, and advanced manufacturing.	`E310911`	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: Department of Mechanical Engineering (University of Michigan) | Statement: [College of Engineering (University of Michigan), hasUnit, Department of Mechanical Engineering (University of Michigan)]

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

Target entity: Department of Mechanical Engineering (University of Michigan)
Context triple: [College of Engineering (University of Michigan), hasUnit, Department of Mechanical Engineering (University of Michigan)]

A. Department of Mechanical Engineering (Carnegie Mellon University)
The Department of Mechanical Engineering at Carnegie Mellon University is a leading academic and research unit known for its strengths in robotics, energy systems, advanced manufacturing, and computational engineering.
B. Department of Mechanical Engineering
The Department of Mechanical Engineering at MIT is a leading academic and research department focused on advancing mechanical sciences, engineering design, and innovation across areas such as robotics, energy, manufacturing, and ocean engineering.
C. Department of Mechanical Engineering
The Department of Mechanical Engineering at UC Berkeley is a leading academic and research unit focused on advancing mechanical sciences and engineering through innovative education and cutting-edge research.
D. Department of Mechanical Engineering
The Department of Mechanical Engineering at McGill University is an academic unit that offers education and conducts research in areas such as mechanics, materials, thermofluids, and design within the Faculty of Engineering.
E. Department of Mechanical Engineering
The Department of Mechanical Engineering at the University of Tokyo is a leading academic and research unit specializing in the science and engineering of mechanical systems, materials, and 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: Department of Mechanical Engineering (University of Michigan)
Triple: [College of Engineering (University of Michigan), hasUnit, Department of Mechanical Engineering (University of Michigan)]

Generated description

The Department of Mechanical Engineering at the University of Michigan is a leading academic and research department known for its work in areas such as automotive engineering, robotics, energy systems, and advanced manufacturing.

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

Target entity: Department of Mechanical Engineering (University of Michigan)
Target entity description: The Department of Mechanical Engineering at the University of Michigan is a leading academic and research department known for its work in areas such as automotive engineering, robotics, energy systems, and advanced manufacturing.

A. Department of Mechanical Engineering (Carnegie Mellon University)
The Department of Mechanical Engineering at Carnegie Mellon University is a leading academic and research unit known for its strengths in robotics, energy systems, advanced manufacturing, and computational engineering.
B. Department of Mechanical Engineering
The Department of Mechanical Engineering at MIT is a leading academic and research department focused on advancing mechanical sciences, engineering design, and innovation across areas such as robotics, energy, manufacturing, and ocean engineering.
C. Department of Mechanical Engineering
The Department of Mechanical Engineering at McGill University is an academic unit that offers education and conducts research in areas such as mechanics, materials, thermofluids, and design within the Faculty of Engineering.
D. Department of Mechanical Engineering
The Department of Mechanical Engineering at the University of Tokyo is a leading academic and research unit specializing in the science and engineering of mechanical systems, materials, and technologies.
E. Department of Mechanical Engineering
The Department of Mechanical Engineering at UC Berkeley is a leading academic and research unit focused on advancing mechanical sciences and engineering through innovative education and cutting-edge research.
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_69ab4c44ab448190b9411324e8a1fc1d`	completed	March 6, 2026, 9:51 p.m.
NER	Named-entity recognition	`batch_69abe0edb1ac81908b22ef60abb4a4df`	completed	March 7, 2026, 8:25 a.m.
NED1	Entity disambiguation (via context triple)	`batch_69b056249b5c8190b388088bf047616f`	completed	March 10, 2026, 5:34 p.m.
NEDg	Description generation	`batch_69b06434bef48190848d8ab1aa59937c`	completed	March 10, 2026, 6:34 p.m.
NED2	Entity disambiguation (via description)	`batch_69b064a3b41481909214a09eae0b092b`	completed	March 10, 2026, 6:36 p.m.

Created at: March 6, 2026, 10:11 p.m.