Triple

T10171827
Position Surface form Disambiguated ID Type / Status
Subject Heidi Hansen E235348 entity
Predicate portrayedByStage P1507 FINISHED
Object Jessica Phillips
Jessica Phillips is an American stage actress best known for her work in Broadway musicals and plays.
E847912 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: Jessica Phillips | Statement: [Heidi Hansen, portrayedByStage, Jessica Phillips]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jessica Phillips
Context triple: [Heidi Hansen, portrayedByStage, Jessica Phillips]
  • A. Stephany Folsom
    Stephany Folsom is an American screenwriter best known for co-writing Pixar’s animated film "Toy Story 4" and contributing to various high-profile film and television projects.
  • B. Rachel Kelley
    Rachel Kelley was the mother of Jesse Root Grant and the paternal grandmother of U.S. President Ulysses S. Grant.
  • C. Nicole Barnhart
    Nicole Barnhart is an American soccer goalkeeper who has played for the U.S. women’s national team and in the National Women's Soccer League.
  • D. Laura Deming
    Laura Deming is a venture capitalist and longevity researcher best known for founding The Longevity Fund, which invests in companies developing therapies to extend healthy human lifespan.
  • E. Christine Weiss
    Christine Weiss is known as the wife of French politician Gérard Larcher, longtime President of the French Senate.
  • 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: Jessica Phillips
Triple: [Heidi Hansen, portrayedByStage, Jessica Phillips]
Generated description
Jessica Phillips is an American stage actress best known for her work in Broadway musicals and plays.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jessica Phillips
Target entity description: Jessica Phillips is an American stage actress best known for her work in Broadway musicals and plays.
  • A. Stephany Folsom
    Stephany Folsom is an American screenwriter best known for co-writing Pixar’s animated film "Toy Story 4" and contributing to various high-profile film and television projects.
  • B. Rachel Kelley
    Rachel Kelley was the mother of Jesse Root Grant and the paternal grandmother of U.S. President Ulysses S. Grant.
  • C. Nicole Barnhart
    Nicole Barnhart is an American soccer goalkeeper who has played for the U.S. women’s national team and in the National Women's Soccer League.
  • D. Laura Deming
    Laura Deming is a venture capitalist and longevity researcher best known for founding The Longevity Fund, which invests in companies developing therapies to extend healthy human lifespan.
  • E. Christine Weiss
    Christine Weiss is known as the wife of French politician Gérard Larcher, longtime President of the French Senate.
  • 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_69ca84ceafd0819085828600e11bed6b completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdec9e4e0c819097dceb7bf7757948 completed April 2, 2026, 4:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d32acbd9ec81908849b17d8ba1dd11 completed April 6, 2026, 3:38 a.m.
NEDg Description generation batch_69d32b88b4b48190b6fd2642a445023a completed April 6, 2026, 3:42 a.m.
NED2 Entity disambiguation (via description) batch_69d32bdede5081908d6f9d18b4ad820e completed April 6, 2026, 3:43 a.m.
Created at: March 30, 2026, 9:10 p.m.