Triple

T17350020
Position Surface form Disambiguated ID Type / Status
Subject Leo McCarey E421782 entity
Predicate directed P7373 FINISHED
Object Once Upon a Honeymoon — NE ONDG

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: Once Upon a Honeymoon | Statement: [Leo McCarey, directed, Once Upon a Honeymoon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Once Upon a Honeymoon
Context triple: [Leo McCarey, directed, Once Upon a Honeymoon]
  • A. The Honeymoon
    The Honeymoon is a 1917 American silent comedy film directed by Charles Giblyn and starring Constance Talmadge.
  • B. The Honeymoon
    "The Honeymoon" is a novel by Justin Haythe that explores the complexities of love, betrayal, and identity in a richly atmospheric, character-driven narrative.
  • C. Honeymoon
    Honeymoon is a 2015 studio album by American singer-songwriter Lana Del Rey, known for its cinematic, melancholic sound and lush orchestral production.
  • D. Honeymoon
    Honeymoon is a 2014 psychological horror film about a newlywed couple whose romantic getaway unravels into a disturbing and mysterious nightmare.
  • E. Honeymoon Express
    "Honeymoon Express" is a pop/rock single by the duo Wendy & Lisa, known for its melodic hooks and association with their late-1980s work after leaving Prince’s band The Revolution.
  • 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: Once Upon a Honeymoon
Triple: [Leo McCarey, directed, Once Upon a Honeymoon]
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Once Upon a Honeymoon
Target entity description: Once Upon a Honeymoon is a 1942 romantic comedy-drama film starring Cary Grant and Ginger Rogers that blends romance, humor, and wartime intrigue.
  • A. The Honeymoon
    "The Honeymoon" is a novel by Justin Haythe that explores the complexities of love, betrayal, and identity in a richly atmospheric, character-driven narrative.
  • B. The Honeymoon
    The Honeymoon is a 1917 American silent comedy film directed by Charles Giblyn and starring Constance Talmadge.
  • C. Honeymoon
    Honeymoon is a 2015 studio album by American singer-songwriter Lana Del Rey, known for its cinematic, melancholic sound and lush orchestral production.
  • D. Honeymoon
    Honeymoon is a 2014 psychological horror film about a newlywed couple whose romantic getaway unravels into a disturbing and mysterious nightmare.
  • E. Honeymoon Express
    "Honeymoon Express" is a pop/rock single by the duo Wendy & Lisa, known for its melodic hooks and association with their late-1980s work after leaving Prince’s band The Revolution.
  • F. None of above. chosen

Provenance (4 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a2bd0a881909e71c89773d9273c completed April 19, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0195585e5881909b0ad386b65112ba completed May 11, 2026, 8:37 a.m.
NEDg Description generation batch_6a0195c365348190bc5ae9d39094e6f3 in_progress May 11, 2026, 8:39 a.m.
Created at: April 10, 2026, 5:44 a.m.