Triple

T19568510
Position Surface form Disambiguated ID Type / Status
Subject Citizen Koch E489648 entity
Predicate producer P490 FINISHED
Object Marilyn Ness
Marilyn Ness is an Emmy-winning documentary film producer and director known for socially engaged works such as "Charm City" and "Trapped."
 E1383625 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: Marilyn Ness | Statement: [Citizen Koch, producer, Marilyn Ness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marilyn Ness
Context triple: [Citizen Koch, producer, Marilyn Ness]
  • A. Marilyn Nash
    Marilyn Nash was an American actress best known for her film debut opposite Charlie Chaplin in the dark comedy "Monsieur Verdoux" (1947).
  • B. Marilyn Vance
    Marilyn Vance is an American costume designer known for her influential work on numerous popular films, including iconic 1980s and 1990s movies.
  • C. Marilyn Seeman
    Marilyn Seeman is known as the wife of longtime NFL officiating executive Jerry Seeman.
  • D. Johnette Howard
    Johnette Howard is an American sports journalist and author known for her insightful writing on athletes and sports culture.
  • E. Marilyn Louis
    Marilyn Louis, better known by her stage name Rhonda Fleming, was an American film and television actress celebrated as one of Hollywood’s most glamorous redheads during the 1940s and 1950s.
  • 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: Marilyn Ness
Triple: [Citizen Koch, producer, Marilyn Ness]
Generated description
Marilyn Ness is an Emmy-winning documentary film producer and director known for socially engaged works such as "Charm City" and "Trapped."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marilyn Ness
Target entity description: Marilyn Ness is an Emmy-winning documentary film producer and director known for socially engaged works such as "Charm City" and "Trapped."
  • A. Marilyn Nash
    Marilyn Nash was an American actress best known for her film debut opposite Charlie Chaplin in the dark comedy "Monsieur Verdoux" (1947).
  • B. Marilyn Vance
    Marilyn Vance is an American costume designer known for her influential work on numerous popular films, including iconic 1980s and 1990s movies.
  • C. Marilyn Seeman
    Marilyn Seeman is known as the wife of longtime NFL officiating executive Jerry Seeman.
  • D. Johnette Howard
    Johnette Howard is an American sports journalist and author known for her insightful writing on athletes and sports culture.
  • E. Marilyn Louis
    Marilyn Louis, better known by her stage name Rhonda Fleming, was an American film and television actress celebrated as one of Hollywood’s most glamorous redheads during the 1940s and 1950s.
  • 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_69d8e8dd9374819098e36349b3211663 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e63f79adf08190b1c0b008f30b0acd completed April 20, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0757898214819090d82acf3fd830ff completed May 15, 2026, 5:27 p.m.
NEDg Description generation batch_6a075865eaac819085b35d165fda91d4 completed May 15, 2026, 5:31 p.m.
NED2 Entity disambiguation (via description) batch_6a07590b84488190a33889335ba95c95 completed May 15, 2026, 5:34 p.m.
Created at: April 10, 2026, 1:42 p.m.