Triple

T8993848

Position	Surface form	Disambiguated ID	Type / Status
Subject	Cornell University Library system	`E214851`	entity
Predicate	hasPart	`P35`	FINISHED
Object	Engineering Library (Cornell University) The Engineering Library at Cornell University is a specialized academic library that supports the research and instructional needs of the College of Engineering and related technical disciplines.	`E771705`	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: Engineering Library (Cornell University) | Statement: [Cornell University Library system, hasPart, Engineering Library (Cornell University)]

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

Target entity: Engineering Library (Cornell University)
Context triple: [Cornell University Library system, hasPart, Engineering Library (Cornell University)]

A. Engineering and Science Library
The Engineering and Science Library is a specialized branch of Queen's University’s library system that supports teaching and research in engineering and scientific disciplines.
B. College of Engineering, Cornell University
The College of Engineering at Cornell University is a leading Ivy League engineering school known for its rigorous programs, cutting-edge research, and contributions across a wide range of engineering disciplines.
C. Cornell University Library system
The Cornell University Library system is the network of libraries serving Cornell University, providing extensive research collections, digital resources, and academic support across its campuses.
D. Engineering and Physical Sciences Library
The Engineering and Physical Sciences Library is a specialized academic library at the University of Canterbury that supports teaching and research in engineering and the physical sciences.
E. Grainger Engineering Library Information Center
The Grainger Engineering Library Information Center is a major academic library at the University of Illinois at Urbana–Champaign renowned for its extensive engineering and science collections and technology-focused study spaces.
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: Engineering Library (Cornell University)
Triple: [Cornell University Library system, hasPart, Engineering Library (Cornell University)]

Generated description

The Engineering Library at Cornell University is a specialized academic library that supports the research and instructional needs of the College of Engineering and related technical disciplines.

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

Target entity: Engineering Library (Cornell University)
Target entity description: The Engineering Library at Cornell University is a specialized academic library that supports the research and instructional needs of the College of Engineering and related technical disciplines.

A. Engineering and Science Library
The Engineering and Science Library is a specialized branch of Queen's University’s library system that supports teaching and research in engineering and scientific disciplines.
B. College of Engineering, Cornell University
The College of Engineering at Cornell University is a leading Ivy League engineering school known for its rigorous programs, cutting-edge research, and contributions across a wide range of engineering disciplines.
C. Cornell University Library system
The Cornell University Library system is the network of libraries serving Cornell University, providing extensive research collections, digital resources, and academic support across its campuses.
D. Engineering and Physical Sciences Library
The Engineering and Physical Sciences Library is a specialized academic library at the University of Canterbury that supports teaching and research in engineering and the physical sciences.
E. Grainger Engineering Library Information Center
The Grainger Engineering Library Information Center is a major academic library at the University of Illinois at Urbana–Champaign renowned for its extensive engineering and science collections and technology-focused study spaces.
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_69ca83a05c608190bdfdbdb25e994b39`	completed	March 30, 2026, 2:07 p.m.
NER	Named-entity recognition	`batch_69cc687798a881908e6fdd9a39219f1d`	completed	April 1, 2026, 12:36 a.m.
NED1	Entity disambiguation (via context triple)	`batch_69cfd0cd2b948190947a26fe11ad81bf`	completed	April 3, 2026, 2:38 p.m.
NEDg	Description generation	`batch_69cfd27680408190a5ebcebacf9e4303`	completed	April 3, 2026, 2:45 p.m.
NED2	Entity disambiguation (via description)	`batch_69cfd2dbf3cc81909589bd9467239573`	completed	April 3, 2026, 2:46 p.m.

Created at: March 30, 2026, 7:04 p.m.