Triple

T10738627
Position Surface form Disambiguated ID Type / Status
Subject Männerpension E253260 entity
Predicate hasCastMember P2308 FINISHED
Object Ingrid van Bergen
Ingrid van Bergen is a German actress known for her extensive film and television career since the 1950s, often portraying strong, charismatic women.
E883193 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: Ingrid van Bergen | Statement: [Männerpension, hasCastMember, Ingrid van Bergen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ingrid van Bergen
Context triple: [Männerpension, hasCastMember, Ingrid van Bergen]
  • A. Astrid Nienhuis
    Astrid Nienhuis is a Dutch politician who serves as the mayor of the municipality of Heemstede in the Netherlands.
  • B. Sjoukje Ozinga
    Sjoukje Ozinga was the mother of Saskia van Uylenburgh, the Dutch woman best known as the wife and muse of painter Rembrandt van Rijn.
  • C. Johanna de Jongh
    Johanna de Jongh was the wife of Dutch Golden Age painter Jan Asselijn, about whom little is historically documented beyond her marital connection to the artist.
  • D. Maria van den Boogaard
    Maria van den Boogaard was the wife of Dutch politician and former Prime Minister Louis Beel.
  • E. Maayke Velders
    Maayke Velders is known primarily as the spouse of Dutch naval hero Michiel de Ruyter.
  • 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: Ingrid van Bergen
Triple: [Männerpension, hasCastMember, Ingrid van Bergen]
Generated description
Ingrid van Bergen is a German actress known for her extensive film and television career since the 1950s, often portraying strong, charismatic women.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ingrid van Bergen
Target entity description: Ingrid van Bergen is a German actress known for her extensive film and television career since the 1950s, often portraying strong, charismatic women.
  • A. Astrid Nienhuis
    Astrid Nienhuis is a Dutch politician who serves as the mayor of the municipality of Heemstede in the Netherlands.
  • B. Sjoukje Ozinga
    Sjoukje Ozinga was the mother of Saskia van Uylenburgh, the Dutch woman best known as the wife and muse of painter Rembrandt van Rijn.
  • C. Johanna de Jongh
    Johanna de Jongh was the wife of Dutch Golden Age painter Jan Asselijn, about whom little is historically documented beyond her marital connection to the artist.
  • D. Maria van den Boogaard
    Maria van den Boogaard was the wife of Dutch politician and former Prime Minister Louis Beel.
  • E. Maayke Velders
    Maayke Velders is known primarily as the spouse of Dutch naval hero Michiel de Ruyter.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d710424d8c81908ee9b59d622f2af5 completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69de22ed6edc8190beb76bd2971c7cec completed April 14, 2026, 11:20 a.m.
NEDg Description generation batch_69de25d25474819081402b75ef7492f6 completed April 14, 2026, 11:32 a.m.
NED2 Entity disambiguation (via description) batch_69de2808244c8190bdb2d4d49f30e0d7 completed April 14, 2026, 11:42 a.m.
Created at: April 8, 2026, 9:14 p.m.