Triple

T14839324
Position Surface form Disambiguated ID Type / Status
Subject Delphine Seyrig E348915 entity
Predicate workedWith P398 FINISHED
Object Harry Kümel
Harry Kümel is a Belgian film director best known for his cult 1971 vampire film "Daughters of Darkness."
E1136602 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: Harry Kümel | Statement: [Delphine Seyrig, workedWith, Harry Kümel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Harry Kümel
Context triple: [Delphine Seyrig, workedWith, Harry Kümel]
  • A. Rolf Schrömgens
    Rolf Schrömgens is a German entrepreneur best known as a co-founder of the global hotel and accommodation search platform Trivago.
  • B. Kurt Christoph
    Kurt Christoph was an 18th-century Prussian field marshal renowned for his leadership in the Silesian Wars under Frederick the Great.
  • C. Heino Kuhn
    Heino Kuhn is a South African cricketer and wicketkeeper-batsman known for his prolific domestic career and appearances for the national team in Test and limited-overs formats.
  • D. Manfred Schnelldorfer
    Manfred Schnelldorfer is a German figure skater best known for winning the men's singles gold medal at the 1964 Winter Olympics.
  • E. Benno Fürmann
    Benno Fürmann is a German actor known for his work in both domestic cinema and international productions, including roles in films like "Speed Racer" and "The Princess and the Warrior."
  • 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: Harry Kümel
Triple: [Delphine Seyrig, workedWith, Harry Kümel]
Generated description
Harry Kümel is a Belgian film director best known for his cult 1971 vampire film "Daughters of Darkness."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Harry Kümel
Target entity description: Harry Kümel is a Belgian film director best known for his cult 1971 vampire film "Daughters of Darkness."
  • A. Rolf Schrömgens
    Rolf Schrömgens is a German entrepreneur best known as a co-founder of the global hotel and accommodation search platform Trivago.
  • B. Kurt Christoph
    Kurt Christoph was an 18th-century Prussian field marshal renowned for his leadership in the Silesian Wars under Frederick the Great.
  • C. Heino Kuhn
    Heino Kuhn is a South African cricketer and wicketkeeper-batsman known for his prolific domestic career and appearances for the national team in Test and limited-overs formats.
  • D. Manfred Schnelldorfer
    Manfred Schnelldorfer is a German figure skater best known for winning the men's singles gold medal at the 1964 Winter Olympics.
  • E. Benno Fürmann
    Benno Fürmann is a German actor known for his work in both domestic cinema and international productions, including roles in films like "Speed Racer" and "The Princess and the Warrior."
  • 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_69d822ec69008190a9232caa68836872 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69ded28e40f08190b309d8ac6404d2fc completed April 14, 2026, 11:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae005644819098937cedb53202c5 completed May 9, 2026, 3:46 a.m.
NEDg Description generation batch_69feaed6acc881909a70376ea3805935 completed May 9, 2026, 3:49 a.m.
NED2 Entity disambiguation (via description) batch_69feb014d9108190b7417f0b3c1838f5 completed May 9, 2026, 3:55 a.m.
Created at: April 10, 2026, 1:52 a.m.