Triple

T16974583
Position Surface form Disambiguated ID Type / Status
Subject Lee Sun-kyun E411776 entity
Predicate notableWork P4 FINISHED
Object Killing Romance
Killing Romance is a South Korean film featuring actor Lee Sun-kyun in a prominent role.
E1242693 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: Killing Romance | Statement: [Lee Sun-kyun, notableWork, Killing Romance]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Killing Romance
Context triple: [Lee Sun-kyun, notableWork, Killing Romance]
  • A. A Love to Kill
    A Love to Kill is a South Korean television drama series starring Rain as a troubled fighter who seeks revenge but becomes entangled in a tragic love story.
  • B. Menacing Love
    Menacing Love is a celebrated 18th-century Rococo sculpture by Étienne-Maurice Falconet depicting a mischievous Cupid poised to shoot his arrow.
  • C. The Death Kiss
    The Death Kiss is a 1932 pre-Code mystery film best known for reuniting several stars of the original Dracula in a story about a murder on a movie set.
  • D. The Crimes of Love
    The Crimes of Love is a collection of short stories by the Marquis de Sade that blends gothic melodrama with philosophical explorations of desire, morality, and cruelty.
  • E. Got Love to Kill
    "Got Love to Kill" is a rock song by the American band Juliette and the Licks, fronted by actress and singer Juliette Lewis.
  • 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: Killing Romance
Triple: [Lee Sun-kyun, notableWork, Killing Romance]
Generated description
Killing Romance is a South Korean film featuring actor Lee Sun-kyun in a prominent role.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Killing Romance
Target entity description: Killing Romance is a South Korean film featuring actor Lee Sun-kyun in a prominent role.
  • A. A Love to Kill
    A Love to Kill is a South Korean television drama series starring Rain as a troubled fighter who seeks revenge but becomes entangled in a tragic love story.
  • B. Menacing Love
    Menacing Love is a celebrated 18th-century Rococo sculpture by Étienne-Maurice Falconet depicting a mischievous Cupid poised to shoot his arrow.
  • C. The Death Kiss
    The Death Kiss is a 1932 pre-Code mystery film best known for reuniting several stars of the original Dracula in a story about a murder on a movie set.
  • D. The Crimes of Love
    The Crimes of Love is a collection of short stories by the Marquis de Sade that blends gothic melodrama with philosophical explorations of desire, morality, and cruelty.
  • E. Got Love to Kill
    "Got Love to Kill" is a rock song by the American band Juliette and the Licks, fronted by actress and singer Juliette Lewis.
  • 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_69d886ca8f348190812768ea8d5055ce completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e3d18300c8819080c8bf19962754ba completed April 18, 2026, 6:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00d4738fbc819099e8281ebc777091 completed May 10, 2026, 6:54 p.m.
NEDg Description generation batch_6a00d51835c48190b1a37de6ac25ceaa completed May 10, 2026, 6:57 p.m.
NED2 Entity disambiguation (via description) batch_6a00d59b96108190a0e55f01529a0b64 completed May 10, 2026, 6:59 p.m.
Created at: April 10, 2026, 5:31 a.m.