Triple

T3023015
Position Surface form Disambiguated ID Type / Status
Subject Friendly Persuasion E82507 entity
Predicate starring P1507 FINISHED
Object Phyllis Love
Phyllis Love was an American stage and screen actress known for her work in mid-20th-century films and Broadway productions.
E356214 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: Phyllis Love | Statement: [Friendly Persuasion, starring, Phyllis Love]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Phyllis Love
Context triple: [Friendly Persuasion, starring, Phyllis Love]
  • A. Phyllis Holden
    Phyllis Holden was an American occupational therapist best known as the first wife of longtime U.S. Senator and 1996 Republican presidential nominee Bob Dole.
  • B. Phyllis Coates
    Phyllis Coates is an American actress best known for playing Lois Lane in the early 1950s Superman film and television adaptations.
  • C. Phyllis Stephens
    Phyllis Stephens is an individual known primarily through her family connection to Wren Alexander Stephens.
  • D. Phyllis Ames
    Phyllis Ames was the wife of Archibald Cox, the prominent American lawyer and Watergate special prosecutor.
  • E. Verna Felton
    Verna Felton was an American character actress and voice performer best known for her memorable roles in classic Disney animated films.
  • 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: Phyllis Love
Triple: [Friendly Persuasion, starring, Phyllis Love]
Generated description
Phyllis Love was an American stage and screen actress known for her work in mid-20th-century films and Broadway productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Phyllis Love
Target entity description: Phyllis Love was an American stage and screen actress known for her work in mid-20th-century films and Broadway productions.
  • A. Phyllis Holden
    Phyllis Holden was an American occupational therapist best known as the first wife of longtime U.S. Senator and 1996 Republican presidential nominee Bob Dole.
  • B. Phyllis Coates
    Phyllis Coates is an American actress best known for playing Lois Lane in the early 1950s Superman film and television adaptations.
  • C. Phyllis Stephens
    Phyllis Stephens is an individual known primarily through her family connection to Wren Alexander Stephens.
  • D. Phyllis Ames
    Phyllis Ames was the wife of Archibald Cox, the prominent American lawyer and Watergate special prosecutor.
  • E. Verna Felton
    Verna Felton was an American character actress and voice performer best known for her memorable roles in classic Disney animated films.
  • 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_69ad8b1fb34081908c1b873e2b7273e1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9ab8e0a48190ac79e674abd181cf completed March 8, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b354505574819083ae7d36e461366b completed March 13, 2026, 12:03 a.m.
NEDg Description generation batch_69b35546dfa0819081800009fbe8afe3 completed March 13, 2026, 12:07 a.m.
NED2 Entity disambiguation (via description) batch_69b355cecc4c81908ecb5f83e89b4a00 completed March 13, 2026, 12:09 a.m.
Created at: March 8, 2026, 3 p.m.