Triple

T1678087
Position Surface form Disambiguated ID Type / Status
Subject Yesterday E36277 entity
Predicate starring P1507 FINISHED
Object Lily James
Lily James is an English actress known for her roles in films such as Cinderella, Baby Driver, and Mamma Mia! Here We Go Again, as well as the TV series Downton Abbey.
E190401 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: Lily James | Statement: [Yesterday, starring, Lily James]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lily James
Context triple: [Yesterday, starring, Lily James]
  • A. Tamsin Egerton
    Tamsin Egerton is an English actress and model known for roles in films such as "St Trinian's," "Keeping Mum," and "The Look of Love."
  • B. Katherine Hoult
    Katherine Hoult is known as the spouse of Richard Mather.
  • C. Jodie Comer
    Jodie Comer is an English actress best known for her critically acclaimed, chameleonic performance as assassin Villanelle in the television series "Killing Eve."
  • D. Anya Taylor-Joy
    Anya Taylor-Joy is an award-winning actress known for her breakout role in "The Queen's Gambit" and performances in films such as "The Witch," "Split," and "Last Night in Soho."
  • E. Imogen Poots
    Imogen Poots is a British actress known for her versatile performances in films such as "Green Room," "28 Weeks Later," and "Need for Speed."
  • 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: Lily James
Triple: [Yesterday, starring, Lily James]
Generated description
Lily James is an English actress known for her roles in films such as Cinderella, Baby Driver, and Mamma Mia! Here We Go Again, as well as the TV series Downton Abbey.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lily James
Target entity description: Lily James is an English actress known for her roles in films such as Cinderella, Baby Driver, and Mamma Mia! Here We Go Again, as well as the TV series Downton Abbey.
  • A. Tamsin Egerton
    Tamsin Egerton is an English actress and model known for roles in films such as "St Trinian's," "Keeping Mum," and "The Look of Love."
  • B. Katherine Hoult
    Katherine Hoult is known as the spouse of Richard Mather.
  • C. Jodie Comer
    Jodie Comer is an English actress best known for her critically acclaimed, chameleonic performance as assassin Villanelle in the television series "Killing Eve."
  • D. Anya Taylor-Joy
    Anya Taylor-Joy is an award-winning actress known for her breakout role in "The Queen's Gambit" and performances in films such as "The Witch," "Split," and "Last Night in Soho."
  • E. Imogen Poots
    Imogen Poots is a British actress known for her versatile performances in films such as "Green Room," "28 Weeks Later," and "Need for Speed."
  • 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_69a886139ed081909af0940aa9313512 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa625f7e1081909c3c4fe76625783a completed March 6, 2026, 5:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad71ba4db08190a532fb334fd0cd23 completed March 8, 2026, 12:55 p.m.
NEDg Description generation batch_69ad73cfce488190b0ed6b85713281d3 completed March 8, 2026, 1:04 p.m.
NED2 Entity disambiguation (via description) batch_69ad74401cbc8190bfaba1e9f32810bc completed March 8, 2026, 1:06 p.m.
Created at: March 4, 2026, 7:29 p.m.