Triple

T23072101

Position	Surface form	Disambiguated ID	Type / Status
Subject	south bank of Rotterdam	`E575223`	entity
Predicate	contains	`P35`	FINISHED
Object	Erasmus MC location Zuid (Ikazia / Maasstad vicinity)? Erasmus MC location Zuid (Ikazia / Maasstad vicinity) is a satellite facility of Erasmus University Medical Center situated on the south bank of Rotterdam near the Ikazia and Maasstad hospitals.	`E1569490`	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: Erasmus MC location Zuid (Ikazia / Maasstad vicinity)? | Statement: [south bank of Rotterdam, contains, Erasmus MC location Zuid (Ikazia / Maasstad vicinity)?]

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

Target entity: Erasmus MC location Zuid (Ikazia / Maasstad vicinity)?
Context triple: [south bank of Rotterdam, contains, Erasmus MC location Zuid (Ikazia / Maasstad vicinity)?]

A. Maastricht University Medical Center+
Maastricht University Medical Center+ is a major academic hospital and research institution in Maastricht, the Netherlands, known for integrating patient care, medical education, and biomedical research.
B. Máxima Medisch Centrum Veldhoven
Máxima Medisch Centrum Veldhoven is a major Dutch hospital in Veldhoven known for providing comprehensive medical care, including specialized services in areas such as obstetrics, neonatology, and oncology.
C. University Medical Center Utrecht
University Medical Center Utrecht is a major Dutch academic hospital and biomedical research center that serves as the primary teaching hospital for Utrecht University.
D. Amsterdam Zuid
Amsterdam Zuid is a major railway and business district station in the southern part of Amsterdam, serving as a key hub for regional and international connections.
E. Roeterseiland Campus
Roeterseiland Campus is a central University of Amsterdam campus area that houses several faculties and modern teaching and research facilities, including those for the social and behavioural sciences.
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: Erasmus MC location Zuid (Ikazia / Maasstad vicinity)?
Triple: [south bank of Rotterdam, contains, Erasmus MC location Zuid (Ikazia / Maasstad vicinity)?]

Generated description

Erasmus MC location Zuid (Ikazia / Maasstad vicinity) is a satellite facility of Erasmus University Medical Center situated on the south bank of Rotterdam near the Ikazia and Maasstad hospitals.

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

Target entity: Erasmus MC location Zuid (Ikazia / Maasstad vicinity)?
Target entity description: Erasmus MC location Zuid (Ikazia / Maasstad vicinity) is a satellite facility of Erasmus University Medical Center situated on the south bank of Rotterdam near the Ikazia and Maasstad hospitals.

A. Maastricht University Medical Center+
Maastricht University Medical Center+ is a major academic hospital and research institution in Maastricht, the Netherlands, known for integrating patient care, medical education, and biomedical research.
B. Máxima Medisch Centrum Veldhoven
Máxima Medisch Centrum Veldhoven is a major Dutch hospital in Veldhoven known for providing comprehensive medical care, including specialized services in areas such as obstetrics, neonatology, and oncology.
C. University Medical Center Utrecht
University Medical Center Utrecht is a major Dutch academic hospital and biomedical research center that serves as the primary teaching hospital for Utrecht University.
D. Amsterdam Zuid
Amsterdam Zuid is a major railway and business district station in the southern part of Amsterdam, serving as a key hub for regional and international connections.
E. Roeterseiland Campus
Roeterseiland Campus is a central University of Amsterdam campus area that houses several faculties and modern teaching and research facilities, including those for the social and behavioural 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_69e245be28d48190ad1348d5a73db37d`	completed	April 17, 2026, 2:37 p.m.
NER	Named-entity recognition	`batch_69f18c5ffad881909ed626045c15dd33`	completed	April 29, 2026, 4:43 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a0c15a941748190b6c44e4a6e6256e2`	completed	May 19, 2026, 7:47 a.m.
NEDg	Description generation	`batch_6a0c1647dc2881909ee6c13b48b71b8d`	completed	May 19, 2026, 7:50 a.m.
NED2	Entity disambiguation (via description)	`batch_6a0c187f6eec81909cf9a62835d56391`	completed	May 19, 2026, 7:59 a.m.

Created at: April 17, 2026, 3:56 p.m.