Triple

T20183504
Position Surface form Disambiguated ID Type / Status
Subject Anaconda (1997 film) E492792 entity
Predicate producer P490 FINISHED
Object Verna Harrah
Verna Harrah was an American film producer and philanthropist, best known for producing genre films in the 1990s and 2000s.
E1415801 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: Verna Harrah | Statement: [Anaconda (1997 film), producer, Verna Harrah]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Verna Harrah
Context triple: [Anaconda (1997 film), producer, Verna Harrah]
  • A. Carrie Laughlin
    Carrie Laughlin is a central character in the 1993 crime thriller film "Kalifornia," which follows a cross-country road trip that turns increasingly dark and violent.
  • B. Lurene Tuttle
    Lurene Tuttle was an American character actress known for her prolific work in radio, film, and television from the 1930s through the 1970s.
  • C. Cissy Yost
    Cissy Yost is a central character in the television series "John from Cincinnati," depicted as a strong-willed matriarch in a troubled surfing family.
  • D. Virgie Mae Tabers
    Virgie Mae Tabers is best known as the mother of American model and television personality Anna Nicole Smith.
  • E. Elsie Magoon
    Elsie Magoon is a literary work by 19th-century American suffragist, abolitionist, and author Frances Dana Barker Gage.
  • 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: Verna Harrah
Triple: [Anaconda (1997 film), producer, Verna Harrah]
Generated description
Verna Harrah was an American film producer and philanthropist, best known for producing genre films in the 1990s and 2000s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Verna Harrah
Target entity description: Verna Harrah was an American film producer and philanthropist, best known for producing genre films in the 1990s and 2000s.
  • A. Carrie Laughlin
    Carrie Laughlin is a central character in the 1993 crime thriller film "Kalifornia," which follows a cross-country road trip that turns increasingly dark and violent.
  • B. Lurene Tuttle
    Lurene Tuttle was an American character actress known for her prolific work in radio, film, and television from the 1930s through the 1970s.
  • C. Cissy Yost
    Cissy Yost is a central character in the television series "John from Cincinnati," depicted as a strong-willed matriarch in a troubled surfing family.
  • D. Virgie Mae Tabers
    Virgie Mae Tabers is best known as the mother of American model and television personality Anna Nicole Smith.
  • E. Elsie Magoon
    Elsie Magoon is a literary work by 19th-century American suffragist, abolitionist, and author Frances Dana Barker Gage.
  • 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_69da6268a034819081cbd9ea5a1c9475 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e668f068748190a0941e98ef5afd59 completed April 20, 2026, 5:57 p.m.
NED1 Entity disambiguation (via context triple) batch_6a083c7febf8819091f9b551b3d3b779 completed May 16, 2026, 9:44 a.m.
NEDg Description generation batch_6a083d3196148190847a625ad09762a2 completed May 16, 2026, 9:47 a.m.
NED2 Entity disambiguation (via description) batch_6a083e04aab88190a1e0219427d8d0e1 completed May 16, 2026, 9:51 a.m.
Created at: April 11, 2026, 11:36 p.m.