Triple

T6217191
Position Surface form Disambiguated ID Type / Status
Subject Comedian Harmonists (film) E139017 entity
Predicate stars P1956 FINISHED
Object Kai Wiesinger
Kai Wiesinger is a German actor known for his roles in film and television, often appearing in historical dramas and popular German cinema.
E577095 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: Kai Wiesinger | Statement: [Comedian Harmonists (film), stars, Kai Wiesinger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kai Wiesinger
Context triple: [Comedian Harmonists (film), stars, Kai Wiesinger]
  • A. Sebastian Knapp
    Sebastian Knapp is an actor best known for his role in the 2013 television miniseries adaptation of the Bible.
  • B. Matthias Kleinheisterkamp
    Matthias Kleinheisterkamp was a high-ranking Waffen-SS officer and division commander during World War II who served in several key SS formations on the Eastern and Western Fronts.
  • C. Maximilian Bittner
    Maximilian Bittner is a German entrepreneur best known as the founding CEO of Lazada, a major Southeast Asian e-commerce platform.
  • D. Sven Wagner
    Sven Wagner is a German local politician who serves as the mayor of the town of Aschersleben in Saxony-Anhalt.
  • E. Jonas Schneider
    Jonas Schneider is a researcher in reinforcement learning best known for co-authoring the Hindsight Experience Replay technique for more efficient learning from sparse rewards.
  • 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: Kai Wiesinger
Triple: [Comedian Harmonists (film), stars, Kai Wiesinger]
Generated description
Kai Wiesinger is a German actor known for his roles in film and television, often appearing in historical dramas and popular German cinema.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kai Wiesinger
Target entity description: Kai Wiesinger is a German actor known for his roles in film and television, often appearing in historical dramas and popular German cinema.
  • A. Sebastian Knapp
    Sebastian Knapp is an actor best known for his role in the 2013 television miniseries adaptation of the Bible.
  • B. Matthias Kleinheisterkamp
    Matthias Kleinheisterkamp was a high-ranking Waffen-SS officer and division commander during World War II who served in several key SS formations on the Eastern and Western Fronts.
  • C. Maximilian Bittner
    Maximilian Bittner is a German entrepreneur best known as the founding CEO of Lazada, a major Southeast Asian e-commerce platform.
  • D. Sven Wagner
    Sven Wagner is a German local politician who serves as the mayor of the town of Aschersleben in Saxony-Anhalt.
  • E. Jonas Schneider
    Jonas Schneider is a researcher in reinforcement learning best known for co-authoring the Hindsight Experience Replay technique for more efficient learning from sparse rewards.
  • 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_69c008aecb0c81909984b48f733ce8ae completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c062a35e308190be25c41b02704411 completed March 22, 2026, 9:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69c20db4e0ac8190ba7bca1f9d8ac6df completed March 24, 2026, 4:06 a.m.
NEDg Description generation batch_69c20ff2bb188190baf8a849efc15f87 completed March 24, 2026, 4:15 a.m.
NED2 Entity disambiguation (via description) batch_69c21365f8f48190970555bd9593b5a4 completed March 24, 2026, 4:30 a.m.
Created at: March 22, 2026, 4:21 p.m.