Triple

T4763774
Position Surface form Disambiguated ID Type / Status
Subject White Heat E105759 entity
Predicate storyBy P1955 FINISHED
Object Virginia Kellogg
Virginia Kellogg was an American screenwriter best known for her hard-hitting crime and prison dramas in mid-20th-century Hollywood.
 E640048 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: Virginia Kellogg | Statement: [White Heat, storyBy, Virginia Kellogg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Virginia Kellogg
Context triple: [White Heat, storyBy, Virginia Kellogg]
  • A. Mary Bingham
    Mary Bingham is a notable member of the prominent Bingham family, recognized for her association with this influential lineage.
  • B. Elizabeth Griscom
    Elizabeth Griscom, better known as Betsy Ross, was an American upholsterer and seamstress traditionally credited with sewing the first flag of the United States.
  • C. Mildred McLean Hazen
    Mildred McLean Hazen was an American socialite and Washington, D.C. hostess best known as the wife of Admiral George Dewey.
  • D. Muriel Buck Humphrey
    Muriel Buck Humphrey was an American political figure who briefly served as a U.S. Senator from Minnesota and was the widow of Vice President Hubert H. Humphrey.
  • E. Marjorie Fowler
    Marjorie Fowler was an American film editor known for her work on numerous Hollywood productions from the 1950s through the 1970s.
  • 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: Virginia Kellogg
Triple: [White Heat, storyBy, Virginia Kellogg]
Generated description
Virginia Kellogg was an American screenwriter best known for her hard-hitting crime and prison dramas in mid-20th-century Hollywood.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Virginia Kellogg
Target entity description: Virginia Kellogg was an American screenwriter best known for her hard-hitting crime and prison dramas in mid-20th-century Hollywood.
  • A. Mary Bingham
    Mary Bingham is a notable member of the prominent Bingham family, recognized for her association with this influential lineage.
  • B. Elizabeth Griscom
    Elizabeth Griscom, better known as Betsy Ross, was an American upholsterer and seamstress traditionally credited with sewing the first flag of the United States.
  • C. Mildred McLean Hazen
    Mildred McLean Hazen was an American socialite and Washington, D.C. hostess best known as the wife of Admiral George Dewey.
  • D. Muriel Buck Humphrey
    Muriel Buck Humphrey was an American political figure who briefly served as a U.S. Senator from Minnesota and was the widow of Vice President Hubert H. Humphrey.
  • E. Marjorie Fowler
    Marjorie Fowler was an American film editor known for her work on numerous Hollywood productions from the 1950s through the 1970s.
  • 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_69bd43f14cac819081c7c69803648211 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6530f0648190b76db9964471cfeb completed March 20, 2026, 3:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7941938a88190be049ad13c45f73f completed March 28, 2026, 8:40 a.m.
NEDg Description generation batch_69c794c3df788190a1b9104d07f56c29 completed March 28, 2026, 8:43 a.m.
NED2 Entity disambiguation (via description) batch_69c795862b24819083db36a7f0f00ad4 completed March 28, 2026, 8:47 a.m.
Created at: March 20, 2026, 1:20 p.m.