Triple

T11899897
Position Surface form Disambiguated ID Type / Status
Subject Who Do You Love E283121 entity
Predicate writer P1360 FINISHED
Object Liza Owen
Liza Owen is a British-Cambodian singer-songwriter known for her pop and R&B-influenced writing and collaborations with major contemporary artists.
E970006 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: Liza Owen | Statement: [Who Do You Love, writer, Liza Owen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liza Owen
Context triple: [Who Do You Love, writer, Liza Owen]
  • A. Liza Elliott
    Liza Elliott is the conflicted, high-powered fashion magazine editor whose psychoanalytic journey drives the plot of the musical "Lady in the Dark."
  • B. Liza Todd
    Liza Todd is an American sculptor and the daughter of actress Elizabeth Taylor and producer Mike Todd.
  • C. Rena Owen
    Rena Owen is a New Zealand actress best known for her powerful lead performance as Beth Heke in the acclaimed film "Once Were Warriors."
  • D. Liza Marshall
    Liza Marshall is a British film and television producer known for her work on projects such as "Before I Go to Sleep" and "Temple."
  • E. Liz Rose
    Liz Rose is an American country music songwriter best known for her frequent collaborations with Taylor Swift on several of Swift’s early hit songs.
  • 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: Liza Owen
Triple: [Who Do You Love, writer, Liza Owen]
Generated description
Liza Owen is a British-Cambodian singer-songwriter known for her pop and R&B-influenced writing and collaborations with major contemporary artists.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Liza Owen
Target entity description: Liza Owen is a British-Cambodian singer-songwriter known for her pop and R&B-influenced writing and collaborations with major contemporary artists.
  • A. Liza Elliott
    Liza Elliott is the conflicted, high-powered fashion magazine editor whose psychoanalytic journey drives the plot of the musical "Lady in the Dark."
  • B. Liza Todd
    Liza Todd is an American sculptor and the daughter of actress Elizabeth Taylor and producer Mike Todd.
  • C. Rena Owen
    Rena Owen is a New Zealand actress best known for her powerful lead performance as Beth Heke in the acclaimed film "Once Were Warriors."
  • D. Liza Marshall
    Liza Marshall is a British film and television producer known for her work on projects such as "Before I Go to Sleep" and "Temple."
  • E. Liz Rose
    Liz Rose is an American country music songwriter best known for her frequent collaborations with Taylor Swift on several of Swift’s early hit songs.
  • 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8dd16433881909befca9774bdaab4 completed April 10, 2026, 11:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f60a5753848190b0ab7da327c9aa22 completed May 2, 2026, 2:29 p.m.
NEDg Description generation batch_69f60d434b68819080808f5c80220c9f completed May 2, 2026, 2:42 p.m.
NED2 Entity disambiguation (via description) batch_69f60dc353ac819082cb866f2b81555b completed May 2, 2026, 2:44 p.m.
Created at: April 8, 2026, 9:44 p.m.