Triple

T20055922

Position	Surface form	Disambiguated ID	Type / Status
Subject	Faculty of Social Sciences, University of Latvia	`E499331`	entity
Predicate	hasDepartment	`P35`	FINISHED
Object	Department of Political Science The Department of Political Science at the University of Latvia is an academic unit specializing in the study and research of political systems, public policy, international relations, and related social science fields.	`E1408533`	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 Political Science | Statement: [Faculty of Social Sciences, University of Latvia, hasDepartment, Department of Political Science]

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

Target entity: Department of Political Science
Context triple: [Faculty of Social Sciences, University of Latvia, hasDepartment, Department of Political Science]

A. Department of Political Science
The Department of Political Science at the University of Oslo is a leading academic unit for research and education in political science within Norway’s Faculty of Social Sciences.
B. Department of Political Science
The Department of Political Science at Kyoto University is an academic unit specializing in the study and research of political systems, theory, and public policy within the university’s Faculty of Law.
C. Department of Political Science
The Department of Political Science at Savitribai Phule Pune University is an academic unit dedicated to teaching and research in political theory, comparative politics, public administration, and related fields.
D. Department of Political Science
The Department of Political Science is an academic unit at Elphinstone College that focuses on the study and research of political systems, governance, public policy, and related social sciences.
E. Department of Political Science
The Department of Political Science is an academic unit at Rangapara College dedicated to teaching and research on government, politics, public policy, and political theory.
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 Political Science
Triple: [Faculty of Social Sciences, University of Latvia, hasDepartment, Department of Political Science]

Generated description

The Department of Political Science at the University of Latvia is an academic unit specializing in the study and research of political systems, public policy, international relations, and related social science fields.

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

Target entity: Department of Political Science
Target entity description: The Department of Political Science at the University of Latvia is an academic unit specializing in the study and research of political systems, public policy, international relations, and related social science fields.

A. Department of Political Science
The Department of Political Science is an academic unit that focuses on the study of government, politics, public policy, and political theory within the Faculty of Liberal Arts & Professional Studies.
B. Department of Political Science
The Department of Political Science is an academic unit specializing in the study and research of political systems, governance, and public policy within the Interregional Academy of Personnel Management.
C. Department of Political Science
The Department of Political Science is an academic unit at the University of Louisville that focuses on the study and research of government, politics, and public policy.
D. Department of Political Science
The Department of Political Science is an academic unit that focuses on the systematic study of government, politics, public policy, and political behavior.
E. Department of Political Science
The Department of Political Science is an academic unit at Ravenshaw University dedicated to teaching and research on political systems, governance, public policy, and related social sciences.
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_69da6276bcf48190aabbf279192a5fb4`	completed	April 11, 2026, 3:02 p.m.
NER	Named-entity recognition	`batch_69e66332b300819097f5dca1636e5822`	completed	April 20, 2026, 5:32 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a08160c59948190acdef6a5ec275101`	completed	May 16, 2026, 7 a.m.
NEDg	Description generation	`batch_6a0816d3c71081909138d3144a108266`	completed	May 16, 2026, 7:03 a.m.
NED2	Entity disambiguation (via description)	`batch_6a08179df70c81908ea5bc596a8ba756`	completed	May 16, 2026, 7:07 a.m.

Created at: April 11, 2026, 3:38 p.m.