Triple

T5080692
Position Surface form Disambiguated ID Type / Status
Subject French Kiss E114502 entity
Predicate title P38 FINISHED
Object French Kiss E114502 NE FINISHED

How this triple was built (2 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: French Kiss | Statement: [French Kiss, title, French Kiss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: French Kiss
Context triple: [French Kiss, title, French Kiss]
  • A. French Kiss chosen
    French Kiss is a 1995 romantic comedy film starring Meg Ryan and Kevin Kline, centered on a woman who travels to France to confront her unfaithful fiancé and becomes entangled with a charming French thief.
  • B. Last Kiss
    "Last Kiss" is a popular rock ballad famously covered by Pearl Jam, known for its tragic narrative and success as one of the band's biggest hit singles.
  • C. Just One Kiss
    "Just One Kiss" is a song featured on the album "The Way I See It."
  • D. Kiss Me
    "Kiss Me" is the smooth, jazz-influenced theme song best known for its use in the opening credits of the classic American sitcom *The Cosby Show*.
  • E. First Kiss
    "First Kiss" is a 2015 rock album by American musician Kid Rock that blends heartland rock, country, and classic rock influences.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69bd443dbf908190a9401e9c2dc7bd7d completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd74f9d9848190919aad6cfe14f1cf completed March 20, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69beb1303bc4819084e0270a8ff97aec completed March 21, 2026, 2:54 p.m.
Created at: March 20, 2026, 1:39 p.m.