Triple

T31500609

Position	Surface form	Disambiguated ID	Type / Status
Subject	Max Rostal	`E803668`	entity
Predicate	taughtAt	`P1203`	FINISHED
Object	Hochschule für Musik und Tanz Köln Hochschule für Musik und Tanz Köln is a renowned German conservatory in Cologne specializing in higher education and professional training in music and dance.	`E121939`	NE FINISHED

How this triple was built (2 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: Hochschule für Musik und Tanz Köln | Statement: [Max Rostal, taughtAt, Hochschule für Musik und Tanz Köln]

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: Hochschule für Musik und Tanz Köln
Triple: [Max Rostal, taughtAt, Hochschule für Musik und Tanz Köln]

Generated description

Hochschule für Musik und Tanz Köln is a renowned German conservatory in Cologne specializing in higher education and professional training in music and dance.

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_69f348cae52081909fa8e5f697523ae3`	completed	April 30, 2026, 12:19 p.m.
NER	Named-entity recognition	`batch_69f6a1ed917c8190916ec726aad9fdec`	completed	May 3, 2026, 1:16 a.m.
NED1	Entity disambiguation (via context triple)	`batch_6a2b146eacc881909a67730c6139d217`	completed	June 11, 2026, 8:02 p.m.
NEDg	Description generation	`batch_6a2b17844ab881909814fb8eff371951`	completed	June 11, 2026, 8:16 p.m.
NED2	Entity disambiguation (via description)	`batch_6a2b1d3082808190bbe7ac5a79b00439`	completed	June 11, 2026, 8:40 p.m.

Created at: April 30, 2026, 9:44 p.m.