Triple

T2250509
Position Surface form Disambiguated ID Type / Status
Subject Philip Seymour Hoffman E49604 entity
Predicate notableWork P4 FINISHED
Object Love Liza
Love Liza is a 2002 independent drama film starring Philip Seymour Hoffman as a grieving widower spiraling into gasoline huffing after his wife's suicide.
 E246583 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: Love Liza | Statement: [Philip Seymour Hoffman, notableWork, Love Liza]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Love Liza
Context triple: [Philip Seymour Hoffman, notableWork, Love Liza]
  • A. Liza
    Liza is a feminine given name most famously associated with American actress and singer Liza Minnelli.
  • B. Liza with a Z
    Liza with a Z is a 1972 television concert film and musical special starring Liza Minnelli, renowned for its dynamic song-and-dance performances and direction by Bob Fosse.
  • C. Liz
    Liz is a common shortened form or nickname for the given name Elizabeth.
  • D. Lilly Belle
    Lilly Belle is a steam locomotive that operates on the Walt Disney World Railroad at the Magic Kingdom theme park in Florida.
  • E. Lady Ella
    Lady Ella is the affectionate nickname of Ella Fitzgerald, the legendary American jazz singer renowned for her pure tone, impeccable diction, and virtuosic scat singing.
  • 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: Love Liza
Triple: [Philip Seymour Hoffman, notableWork, Love Liza]
Generated description
Love Liza is a 2002 independent drama film starring Philip Seymour Hoffman as a grieving widower spiraling into gasoline huffing after his wife's suicide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Love Liza
Target entity description: Love Liza is a 2002 independent drama film starring Philip Seymour Hoffman as a grieving widower spiraling into gasoline huffing after his wife's suicide.
  • A. Liza
    Liza is a feminine given name most famously associated with American actress and singer Liza Minnelli.
  • B. Liza with a Z
    Liza with a Z is a 1972 television concert film and musical special starring Liza Minnelli, renowned for its dynamic song-and-dance performances and direction by Bob Fosse.
  • C. Liz
    Liz is a common shortened form or nickname for the given name Elizabeth.
  • D. Lilly Belle
    Lilly Belle is a steam locomotive that operates on the Walt Disney World Railroad at the Magic Kingdom theme park in Florida.
  • E. Lady Ella
    Lady Ella is the affectionate nickname of Ella Fitzgerald, the legendary American jazz singer renowned for her pure tone, impeccable diction, and virtuosic scat singing.
  • 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_69a88aaa9250819095e127d0d77e8a32 completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc11b61888190af3b11b87dc8e0dc completed March 7, 2026, 6:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b1bc424819087b2ce9a6256a180 completed March 9, 2026, 6:39 a.m.
NEDg Description generation batch_69ae6be0d108819085cf8c531d08db65 completed March 9, 2026, 6:42 a.m.
NED2 Entity disambiguation (via description) batch_69ae6c0fc220819090b254cc20b1bc26 completed March 9, 2026, 6:43 a.m.
Created at: March 4, 2026, 7:47 p.m.