Triple

T33107313

Position	Surface form	Disambiguated ID	Type / Status
Subject	Wittdün auf Amrum	`E847221`	entity
Predicate	hasLocalNameInNorthFrisian	`P196709`	FINISHED
Object	Witjön Witjön is the North Frisian name for Wittdün, a seaside resort village on the German North Sea island of Amrum.	`E2035312`	NE FINISHED

How this triple was built (3 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: Witjön | Statement: [Wittdün auf Amrum, hasLocalNameInNorthFrisian, Witjön]

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: Witjön
Triple: [Wittdün auf Amrum, hasLocalNameInNorthFrisian, Witjön]

Generated description

Witjön is the North Frisian name for Wittdün, a seaside resort village on the German North Sea island of Amrum.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: hasLocalNameInNorthFrisian
Context triple: [Wittdün auf Amrum, hasLocalNameInNorthFrisian, Witjön]

A. WestFrisianName
Indicates that the associated name is the form used in the West Frisian language for the given entity.
B. hasNameInNorthernSami
Indicates that an entity is associated with a specific name expressed in the Northern Sami language.
C. hasFranconianName
Indicates that an entity is associated with a name or designation in the Franconian language or dialect.
D. hasLanguageOnNorthernSide
Indicates that a particular language is used or present on the northern side of a specified boundary, area, or object.
E. hasNameInNorwegian
Indicates that an entity is associated with a specific name expressed in the Norwegian language.
F. None of above. chosen

Provenance (7 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_69f3495686508190b76bf20fa5e00bf7`	completed	April 30, 2026, 12:21 p.m.
NER	Named-entity recognition	`batch_69fe629b4fa481908467c7c41b77f0c6`	completed	May 8, 2026, 10:24 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a34f0330dc081908c7eefbd0858b5d7`	completed	June 19, 2026, 7:30 a.m.
NEDg	Description generation	`batch_6a34fac5b8608190aa4d75308c8e80d0`	completed	June 19, 2026, 8:16 a.m.
NED2	Entity disambiguation (via description)	`batch_6a34fb4c77148190be1f4858389df113`	completed	June 19, 2026, 8:18 a.m.
PD	Predicate disambiguation	`batch_69fe61bb260c819083f9378a3a06ca47`	completed	May 8, 2026, 10:20 p.m.
PDg	Predicate description generation	`batch_69fe629a8d4c8190b4aa4dee39efc0a6`	completed	May 8, 2026, 10:24 p.m.

Created at: May 1, 2026, 1:26 a.m.