Triple

T12531293
Position Surface form Disambiguated ID Type / Status
Subject From Darkness E299568 entity
Predicate castMember P1668 FINISHED
Object Cathrin Bach
Cathrin Bach is an actress known for her role in the television series "From Darkness."
E1010105 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: Cathrin Bach | Statement: [From Darkness, castMember, Cathrin Bach]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Cathrin Bach
Context triple: [From Darkness, castMember, Cathrin Bach]
  • A. Katrin Houben
    Katrin Houben is an individual notable enough to be recognized as a namesake or prominent bearer of the surname Houben.
  • B. Sabine Völker
    Sabine Völker is a German speed skater known for winning an Olympic bronze medal in the 500 m event at the 2002 Winter Games.
  • C. Carolin Emcke
    Carolin Emcke is a German journalist, author, and public intellectual known for her writings on violence, human rights, and social justice.
  • D. Ute Grunert
    Ute Grunert is known as the spouse of Nobel Prize–winning German author Günter Grass.
  • E. Katrin Brenner
    Katrin Brenner is a German local politician who serves as the mayor of the town of Sundern in North Rhine-Westphalia.
  • 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: Cathrin Bach
Triple: [From Darkness, castMember, Cathrin Bach]
Generated description
Cathrin Bach is an actress known for her role in the television series "From Darkness."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Cathrin Bach
Target entity description: Cathrin Bach is an actress known for her role in the television series "From Darkness."
  • A. Katrin Houben
    Katrin Houben is an individual notable enough to be recognized as a namesake or prominent bearer of the surname Houben.
  • B. Sabine Völker
    Sabine Völker is a German speed skater known for winning an Olympic bronze medal in the 500 m event at the 2002 Winter Games.
  • C. Carolin Emcke
    Carolin Emcke is a German journalist, author, and public intellectual known for her writings on violence, human rights, and social justice.
  • D. Ute Grunert
    Ute Grunert is known as the spouse of Nobel Prize–winning German author Günter Grass.
  • E. Katrin Brenner
    Katrin Brenner is a German local politician who serves as the mayor of the town of Sundern in North Rhine-Westphalia.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d95469d100819087c83bc55e3ec9ce completed April 10, 2026, 7:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6a537bb1881908a50073d4f27b66c completed May 3, 2026, 1:30 a.m.
NEDg Description generation batch_69f6a8db611c819086e48afa368df288 completed May 3, 2026, 1:46 a.m.
NED2 Entity disambiguation (via description) batch_69f6a9dc37d08190b658a2e1d8ac2d88 completed May 3, 2026, 1:50 a.m.
Created at: April 8, 2026, 9:57 p.m.