Triple

T5359289
Position Surface form Disambiguated ID Type / Status
Subject Gellert Grindelwald E102778 entity
Predicate imprisonedIn P6022 FINISHED
Object Nurmengard
Nurmengard is a high-security wizarding prison built by the dark wizard Gellert Grindelwald in the Harry Potter universe, later used to confine Grindelwald himself.
E514106 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: Nurmengard | Statement: [Gellert Grindelwald, imprisonedIn, Nurmengard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nurmengard
Context triple: [Gellert Grindelwald, imprisonedIn, Nurmengard]
  • A. Mauregard
    Mauregard is a small commune in the Seine-et-Marne department of the Île-de-France region in north-central France, situated near Paris Charles de Gaulle Airport.
  • B. Vytegra
    Vytegra is a small town in northwestern Russia known as a regional center near Lake Onega and the White Sea–Baltic Canal.
  • C. Syrgenstein
    Syrgenstein is a small municipality in the Heidenheim district of the German state of Baden-Württemberg.
  • D. Thalheim
    Thalheim is a town in the German state of Saxony-Anhalt that was incorporated into the larger city of Bitterfeld-Wolfen.
  • E. Dagmaer
    Dagmaer is a given name, likely a variant of the Scandinavian name Dagmar, used as a personal feminine first name.
  • 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: Nurmengard
Triple: [Gellert Grindelwald, imprisonedIn, Nurmengard]
Generated description
Nurmengard is a high-security wizarding prison built by the dark wizard Gellert Grindelwald in the Harry Potter universe, later used to confine Grindelwald himself.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nurmengard
Target entity description: Nurmengard is a high-security wizarding prison built by the dark wizard Gellert Grindelwald in the Harry Potter universe, later used to confine Grindelwald himself.
  • A. Mauregard
    Mauregard is a small commune in the Seine-et-Marne department of the Île-de-France region in north-central France, situated near Paris Charles de Gaulle Airport.
  • B. Vytegra
    Vytegra is a small town in northwestern Russia known as a regional center near Lake Onega and the White Sea–Baltic Canal.
  • C. Syrgenstein
    Syrgenstein is a small municipality in the Heidenheim district of the German state of Baden-Württemberg.
  • D. Thalheim
    Thalheim is a town in the German state of Saxony-Anhalt that was incorporated into the larger city of Bitterfeld-Wolfen.
  • E. Dagmaer
    Dagmaer is a given name, likely a variant of the Scandinavian name Dagmar, used as a personal feminine first name.
  • 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_69bd43d8f7248190b64c140734b5c9a8 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd86330e4c8190b5452226886287b3 completed March 20, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf21e955a8819094a0b12e42e2d6a6 completed March 21, 2026, 10:55 p.m.
NEDg Description generation batch_69bf23d9ca3881909bfc0a2e99164450 completed March 21, 2026, 11:03 p.m.
NED2 Entity disambiguation (via description) batch_69bf243319448190a30d6e8847d3f4b8 completed March 21, 2026, 11:05 p.m.
Created at: March 20, 2026, 2:02 p.m.