Triple

T9292473
Position Surface form Disambiguated ID Type / Status
Subject Edward James E223552 entity
Predicate spouse P13 FINISHED
Object Tilly Losch
Tilly Losch was an Austrian-born dancer, choreographer, and actress renowned for her innovative modern dance performances on stage and in film during the early 20th century.
 E865994 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: Tilly Losch | Statement: [Edward James, spouse, Tilly Losch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tilly Losch
Context triple: [Edward James, spouse, Tilly Losch]
  • A. Lotta Crabtree
    Lotta Crabtree was a celebrated 19th-century American actress, comedian, and vaudeville star who became one of the highest-paid performers of her era.
  • B. Dorothy Lyman
    Dorothy Lyman is an American actress and director best known for her roles on the soap opera "All My Children" and the sitcom "Mama's Family."
  • C. Dorothy C. Cressman
    Dorothy C. Cressman was the wife of American archaeologist and anthropologist Luther Cressman.
  • D. Ruthanne Fuller
    Ruthanne Fuller is an American politician who serves as the mayor of Newton, Massachusetts.
  • E. Dorothy Miner
    Dorothy Miner was a prominent American art historian and curator known for her influential work with medieval manuscripts at the Walters Art Museum in Baltimore.
  • 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: Tilly Losch
Triple: [Edward James, spouse, Tilly Losch]
Generated description
Tilly Losch was an Austrian-born dancer, choreographer, and actress renowned for her innovative modern dance performances on stage and in film during the early 20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tilly Losch
Target entity description: Tilly Losch was an Austrian-born dancer, choreographer, and actress renowned for her innovative modern dance performances on stage and in film during the early 20th century.
  • A. Lotta Crabtree
    Lotta Crabtree was a celebrated 19th-century American actress, comedian, and vaudeville star who became one of the highest-paid performers of her era.
  • B. Dorothy Lyman
    Dorothy Lyman is an American actress and director best known for her roles on the soap opera "All My Children" and the sitcom "Mama's Family."
  • C. Dorothy C. Cressman
    Dorothy C. Cressman was the wife of American archaeologist and anthropologist Luther Cressman.
  • D. Ruthanne Fuller
    Ruthanne Fuller is an American politician who serves as the mayor of Newton, Massachusetts.
  • E. Dorothy Miner
    Dorothy Miner was a prominent American art historian and curator known for her influential work with medieval manuscripts at the Walters Art Museum in Baltimore.
  • 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_69ca8422ddf881908a3f8f876c9f53aa completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd0866ff608190a07afac4afd0ec09 completed April 1, 2026, 11:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69d89eedc66c81909076cc7ba35f9da5 completed April 10, 2026, 6:55 a.m.
NEDg Description generation batch_69d8a2f4bbec8190a5c508c6431d71b2 completed April 10, 2026, 7:12 a.m.
NED2 Entity disambiguation (via description) batch_69d8aff34c7081909c3504e00f56d9ec completed April 10, 2026, 8:08 a.m.
Created at: March 30, 2026, 7:35 p.m.