Triple

T681023
Position Surface form Disambiguated ID Type / Status
Subject Blood and Sand (1922 film) E13180 entity
Predicate starring P1507 FINISHED
Object Lila Lee
Lila Lee was a popular American silent film actress of the 1910s and 1920s, known for her girl-next-door charm and roles in major productions of the era.
E95059 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: Lila Lee | Statement: [Blood and Sand (1922 film), starring, Lila Lee]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lila Lee
Context triple: [Blood and Sand (1922 film), starring, Lila Lee]
  • A. Cecilia Peck
    Cecilia Peck is an American actress, documentary filmmaker, and producer, and the daughter of legendary actor Gregory Peck.
  • B. Eileen Loo
    Eileen Loo was the wife of renowned Chinese-American architect I. M. Pei and a supportive partner throughout his celebrated career.
  • C. Mary Lee Woods
    Mary Lee Woods was a British mathematician and computer scientist who worked on early computers at Ferranti and was the mother of World Wide Web inventor Tim Berners-Lee.
  • D. Vicky Chun
    Vicky Chun is a collegiate sports administrator best known for serving as the director of athletics at Yale University.
  • E. Gwen Bagni
    Gwen Bagni was an American screenwriter known for her work in mid-20th-century film and television, including adaptations of historical and biographical stories.
  • 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: Lila Lee
Triple: [Blood and Sand (1922 film), starring, Lila Lee]
Generated description
Lila Lee was a popular American silent film actress of the 1910s and 1920s, known for her girl-next-door charm and roles in major productions of the era.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lila Lee
Target entity description: Lila Lee was a popular American silent film actress of the 1910s and 1920s, known for her girl-next-door charm and roles in major productions of the era.
  • A. Cecilia Peck
    Cecilia Peck is an American actress, documentary filmmaker, and producer, and the daughter of legendary actor Gregory Peck.
  • B. Eileen Loo
    Eileen Loo was the wife of renowned Chinese-American architect I. M. Pei and a supportive partner throughout his celebrated career.
  • C. Mary Lee Woods
    Mary Lee Woods was a British mathematician and computer scientist who worked on early computers at Ferranti and was the mother of World Wide Web inventor Tim Berners-Lee.
  • D. Vicky Chun
    Vicky Chun is a collegiate sports administrator best known for serving as the director of athletics at Yale University.
  • E. Gwen Bagni
    Gwen Bagni was an American screenwriter known for her work in mid-20th-century film and television, including adaptations of historical and biographical stories.
  • 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_69a4933d3bf88190972041cd8cf143b9 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a06e294c8190873116a3253e04f9 completed March 1, 2026, 8:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69a68918e87c819085df25ee862ba836 completed March 3, 2026, 7:09 a.m.
NEDg Description generation batch_69a68d097d088190aa19d2857c6419c2 completed March 3, 2026, 7:26 a.m.
NED2 Entity disambiguation (via description) batch_69a6ce6e692081908a49b12729f59a84 completed March 3, 2026, 12:05 p.m.
Created at: March 1, 2026, 7:36 p.m.