Triple

T2604394
Position Surface form Disambiguated ID Type / Status
Subject Best E58622 entity
Predicate hasNotableBearer P458 FINISHED
Object Marjorie Best
Marjorie Best was an American costume designer known for her work in Hollywood films, including her Academy Award–winning designs.
 E480408 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: Marjorie Best | Statement: [Best, hasNotableBearer, Marjorie Best]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marjorie Best
Context triple: [Best, hasNotableBearer, Marjorie Best]
  • A. Marjorie Content
    Marjorie Content was an American photographer and writer associated with early 20th-century modernist and literary circles.
  • B. Marjorie Nelson
    Marjorie Nelson was an American actress known for her work on stage and screen and for being married to fellow actor Howard Da Silva.
  • C. Marjorie Hood
    Marjorie Hood was the first wife of American lyricist and playwright Alan Jay Lerner, known for her marriage to the celebrated Broadway writer.
  • D. Marjorie Reynolds
    Marjorie Reynolds was an American film and television actress best known for her roles in classic 1940s movies and early TV series.
  • E. Marjorie Frost
    Marjorie Frost was one of the daughters of American poet Robert Frost, whose short life was marked by illness and personal tragedy within the Frost family.
  • 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: Marjorie Best
Triple: [Best, hasNotableBearer, Marjorie Best]
Generated description
Marjorie Best was an American costume designer known for her work in Hollywood films, including her Academy Award–winning designs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marjorie Best
Target entity description: Marjorie Best was an American costume designer known for her work in Hollywood films, including her Academy Award–winning designs.
  • A. Marjorie Content
    Marjorie Content was an American photographer and writer associated with early 20th-century modernist and literary circles.
  • B. Marjorie Nelson
    Marjorie Nelson was an American actress known for her work on stage and screen and for being married to fellow actor Howard Da Silva.
  • C. Marjorie Hood
    Marjorie Hood was the first wife of American lyricist and playwright Alan Jay Lerner, known for her marriage to the celebrated Broadway writer.
  • D. Marjorie Reynolds
    Marjorie Reynolds was an American film and television actress best known for her roles in classic 1940s movies and early TV series.
  • E. Marjorie Frost
    Marjorie Frost was one of the daughters of American poet Robert Frost, whose short life was marked by illness and personal tragedy within the Frost family.
  • 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_69ab4ac3523881909679750c9f8c2dec completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd8340eac819084eb1fe6f0ac0aa0 completed March 7, 2026, 7:48 a.m.
NED1 Entity disambiguation (via context triple) batch_69be77765a788190aaf4637ad4cab5ed completed March 21, 2026, 10:48 a.m.
NEDg Description generation batch_69be7885bf60819083f6546234c1c40c completed March 21, 2026, 10:52 a.m.
NED2 Entity disambiguation (via description) batch_69be78f8baf4819097393d670d217b63 completed March 21, 2026, 10:54 a.m.
Created at: March 6, 2026, 9:49 p.m.