Triple

T10870051
Position Surface form Disambiguated ID Type / Status
Subject Evangelical Union E256625 entity
Predicate hasMember P10 FINISHED
Object Nassau-Usingen
Nassau-Usingen was a small principality within the Holy Roman Empire, located in what is now western Germany and historically ruled by a branch of the House of Nassau.
E890675 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: Nassau-Usingen | Statement: [Evangelical Union, hasMember, Nassau-Usingen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nassau-Usingen
Context triple: [Evangelical Union, hasMember, Nassau-Usingen]
  • A. Nassau de Zuylestein
    Nassau de Zuylestein is a Dutch noble family of the House of Orange-Nassau whose members held English titles and played prominent roles in Anglo-Dutch political and court life.
  • B. Ostend
    Ostend is a Belgian coastal city on the North Sea known for its beaches, port, and seaside tourism.
  • C. Ostend
    Ostend is a small residential and commercial settlement on Waiheke Island in New Zealand’s Hauraki Gulf.
  • D. Nassau-Beilstein
    Nassau-Beilstein was a small German county and cadet branch territory of the House of Nassau within the Holy Roman Empire.
  • E. Vandamm
    Vandamm is a surname, often a variant spelling of "van Damm," associated with various individuals in arts, entertainment, and other fields.
  • 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: Nassau-Usingen
Triple: [Evangelical Union, hasMember, Nassau-Usingen]
Generated description
Nassau-Usingen was a small principality within the Holy Roman Empire, located in what is now western Germany and historically ruled by a branch of the House of Nassau.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nassau-Usingen
Target entity description: Nassau-Usingen was a small principality within the Holy Roman Empire, located in what is now western Germany and historically ruled by a branch of the House of Nassau.
  • A. Nassau de Zuylestein
    Nassau de Zuylestein is a Dutch noble family of the House of Orange-Nassau whose members held English titles and played prominent roles in Anglo-Dutch political and court life.
  • B. Ostend
    Ostend is a Belgian coastal city on the North Sea known for its beaches, port, and seaside tourism.
  • C. Ostend
    Ostend is a small residential and commercial settlement on Waiheke Island in New Zealand’s Hauraki Gulf.
  • D. Nassau-Beilstein
    Nassau-Beilstein was a small German county and cadet branch territory of the House of Nassau within the Holy Roman Empire.
  • E. Vandamm
    Vandamm is a surname, often a variant spelling of "van Damm," associated with various individuals in arts, entertainment, and other fields.
  • 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_69d6aa83d1448190a66d93c32394d21f completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7518610e48190bee50db71ae0ca3e completed April 9, 2026, 7:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69dff7d9ce3c8190afeb2a27fb82b594 completed April 15, 2026, 8:40 p.m.
NEDg Description generation batch_69e03cc71a4c81909147945dff371217 completed April 16, 2026, 1:35 a.m.
NED2 Entity disambiguation (via description) batch_69e03dfb02c4819087a697ba7f5a1135 completed April 16, 2026, 1:40 a.m.
Created at: April 8, 2026, 9:20 p.m.