Triple

T9326154
Position Surface form Disambiguated ID Type / Status
Subject Mark Sandrich E224389 entity
Predicate notableWork P4 FINISHED
Object Love on Toast
Love on Toast is a 1937 American romantic comedy film directed by Mark Sandrich.
 E792178 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 on Toast | Statement: [Mark Sandrich, notableWork, Love on Toast]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Love on Toast
Context triple: [Mark Sandrich, notableWork, Love on Toast]
  • A. More Than Toast
    "More Than Toast" is a song featured on the musical theatre album "Carry the Banner."
  • B. Angels on Toast
    Angels on Toast is a satirical novel by American writer Dawn Powell, known for its sharp, witty portrayal of mid-20th-century urban life and social climbing.
  • C. "It's Toasted"
    "It's Toasted" is the famous Lucky Strike advertising slogan emphasizing the brand’s distinctive tobacco toasting process rather than sun-drying.
  • D. Love at First Bite
    Love at First Bite is a 1979 horror-comedy film that parodies the Dracula legend, starring George Hamilton as a suave, romantic Count Dracula navigating modern New York City.
  • E. The Thing About Love
    "The Thing About Love" is a pop ballad by Christina Aguilera from her 2007 album *Back to Basics*, showcasing her soulful vocals and reflective lyrics about the complexities of love.
  • 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 on Toast
Triple: [Mark Sandrich, notableWork, Love on Toast]
Generated description
Love on Toast is a 1937 American romantic comedy film directed by Mark Sandrich.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Love on Toast
Target entity description: Love on Toast is a 1937 American romantic comedy film directed by Mark Sandrich.
  • A. More Than Toast
    "More Than Toast" is a song featured on the musical theatre album "Carry the Banner."
  • B. Angels on Toast
    Angels on Toast is a satirical novel by American writer Dawn Powell, known for its sharp, witty portrayal of mid-20th-century urban life and social climbing.
  • C. "It's Toasted"
    "It's Toasted" is the famous Lucky Strike advertising slogan emphasizing the brand’s distinctive tobacco toasting process rather than sun-drying.
  • D. Love at First Bite
    Love at First Bite is a 1979 horror-comedy film that parodies the Dracula legend, starring George Hamilton as a suave, romantic Count Dracula navigating modern New York City.
  • E. The Thing About Love
    "The Thing About Love" is a pop ballad by Christina Aguilera from her 2007 album *Back to Basics*, showcasing her soulful vocals and reflective lyrics about the complexities of love.
  • 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_69ca8427a0c08190b749831d5ea98f02 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd36f88e988190bb896a3d7c3c723c completed April 1, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69d0c7e940d481909882dd920f0c6c1d completed April 4, 2026, 8:12 a.m.
NEDg Description generation batch_69d0c976a0308190ba66990fe0a3f33e completed April 4, 2026, 8:19 a.m.
NED2 Entity disambiguation (via description) batch_69d0ce28aaf48190a1e6b4040353c6b9 completed April 4, 2026, 8:39 a.m.
Created at: March 30, 2026, 7:39 p.m.