Triple

T16133883
Position Surface form Disambiguated ID Type / Status
Subject Werner Herzog E391470 entity
Predicate spouse P13 FINISHED
Object Martje Grohmann
Martje Grohmann is a German photographer and former wife of renowned filmmaker Werner Herzog.
E1197579 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: Martje Grohmann | Statement: [Werner Herzog, spouse, Martje Grohmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martje Grohmann
Context triple: [Werner Herzog, spouse, Martje Grohmann]
  • A. Johanna Geilus
    Johanna Geilus was the wife of Austrian journalist and politician Fritz Austerlitz.
  • B. Astrid Nienhuis
    Astrid Nienhuis is a Dutch politician who serves as the mayor of the municipality of Heemstede in the Netherlands.
  • C. Thekla Reuten
    Thekla Reuten is a Dutch actress known for her roles in international films and television series, including English-language productions.
  • D. Lida Scholten
    Lida Scholten is a Dutch art patron and co-founder of the Museum Beelden aan Zee in The Hague, known for her support of modern and contemporary sculpture.
  • E. Johanna ter Steege
    Johanna ter Steege is a Dutch actress acclaimed for her powerful performances in European cinema and international films.
  • 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: Martje Grohmann
Triple: [Werner Herzog, spouse, Martje Grohmann]
Generated description
Martje Grohmann is a German photographer and former wife of renowned filmmaker Werner Herzog.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Martje Grohmann
Target entity description: Martje Grohmann is a German photographer and former wife of renowned filmmaker Werner Herzog.
  • A. Johanna Geilus
    Johanna Geilus was the wife of Austrian journalist and politician Fritz Austerlitz.
  • B. Astrid Nienhuis
    Astrid Nienhuis is a Dutch politician who serves as the mayor of the municipality of Heemstede in the Netherlands.
  • C. Thekla Reuten
    Thekla Reuten is a Dutch actress known for her roles in international films and television series, including English-language productions.
  • D. Lida Scholten
    Lida Scholten is a Dutch art patron and co-founder of the Museum Beelden aan Zee in The Hague, known for her support of modern and contemporary sculpture.
  • E. Johanna ter Steege
    Johanna ter Steege is a Dutch actress acclaimed for her powerful performances in European cinema and international films.
  • 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_69d87f1bb0988190b490d273dbf3fd03 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21a039f0c8190a679e16a27f2dbe3 completed April 17, 2026, 11:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7a304348190bf471f2b9279b806 completed May 10, 2026, 3:12 a.m.
NEDg Description generation batch_69fff8de647481908e820b0e14bc7b76 completed May 10, 2026, 3:17 a.m.
NED2 Entity disambiguation (via description) batch_69fff94cd32081908205ae383e58d148 completed May 10, 2026, 3:19 a.m.
Created at: April 10, 2026, 5:01 a.m.