Triple

T2141902
Position Surface form Disambiguated ID Type / Status
Subject Leslie Caron E46776 entity
Predicate notableWork P4 FINISHED
Object Lili
Lili is a 1953 musical fantasy film starring Leslie Caron as a naive orphan who joins a carnival and forms a touching bond with a puppeteer.
 E236631 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: Lili | Statement: [Leslie Caron, notableWork, Lili]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lili
Context triple: [Leslie Caron, notableWork, Lili]
  • A. Lulu
    Lulu is a common feminine given name or nickname, often used as a diminutive form of names like Louise.
  • B. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • C. Lilly Belle
    Lilly Belle is a steam locomotive that operates on the Walt Disney World Railroad at the Magic Kingdom theme park in Florida.
  • D. Lucille
    "Lucille" is a 1977 country song by Kenny Rogers that became one of his signature hits and a classic of the genre.
  • E. Lucille
    Lucille is the famous black Gibson guitar closely associated with blues legend B.B. King, who named all his guitars by this name.
  • 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: Lili
Triple: [Leslie Caron, notableWork, Lili]
Generated description
Lili is a 1953 musical fantasy film starring Leslie Caron as a naive orphan who joins a carnival and forms a touching bond with a puppeteer.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lili
Target entity description: Lili is a 1953 musical fantasy film starring Leslie Caron as a naive orphan who joins a carnival and forms a touching bond with a puppeteer.
  • A. Lulu
    Lulu is a common feminine given name or nickname, often used as a diminutive form of names like Louise.
  • B. Marlene
    Marlene is a German biographical film directed by Joseph Vilsmaier about the life and career of actress and singer Marlene Dietrich.
  • C. Lilly Belle
    Lilly Belle is a steam locomotive that operates on the Walt Disney World Railroad at the Magic Kingdom theme park in Florida.
  • D. Lucille
    "Lucille" is a 1977 country song by Kenny Rogers that became one of his signature hits and a classic of the genre.
  • E. Lucille
    Lucille is the famous black Gibson guitar closely associated with blues legend B.B. King, who named all his guitars by this name.
  • 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_69a88a174ab48190a5db20c132e5dccf completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbe0543108190862dd9a4a861c758 completed March 7, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae51b63e4081908a5d87af5d17d3c4 completed March 9, 2026, 4:51 a.m.
NEDg Description generation batch_69ae52d29d708190809ee4d5047b2755 completed March 9, 2026, 4:55 a.m.
NED2 Entity disambiguation (via description) batch_69ae532ec8808190b1ecd8c4f66df30d completed March 9, 2026, 4:57 a.m.
Created at: March 4, 2026, 7:44 p.m.