Triple

T22555499
Position Surface form Disambiguated ID Type / Status
Subject Yeon Sang-ho E557669 entity
Predicate notableWork P4 FINISHED
Object Train to Busan NE NERFINISHED

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: Train to Busan | Statement: [Yeon Sang-ho, notableWork, Train to Busan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Train to Busan
Context triple: [Yeon Sang-ho, notableWork, Train to Busan]
  • A. Train to Busan chosen
    Train to Busan is a critically acclaimed South Korean zombie thriller film that follows passengers fighting for survival during a viral outbreak on a speeding train.
  • B. Bird Box
    Bird Box is a 2018 post-apocalyptic horror film, starring Sandra Bullock, about a mysterious force that drives people to deadly violence if seen, forcing survivors to navigate the world while blindfolded.
  • C. It Comes at Night
    It Comes at Night is a 2017 psychological horror film about a family struggling to survive a mysterious, deadly contagion in an isolated house.
  • D. World War Z
    World War Z is a 2013 apocalyptic action-horror film starring Brad Pitt that depicts a global zombie pandemic and humanity’s desperate efforts to survive.
  • E. 10 Cloverfield Lane
    10 Cloverfield Lane is a 2016 psychological thriller film set largely in an underground bunker, where a woman questions whether her captor is protecting her from a real outside threat or manipulating her.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e59db848190b4272ecd2b690ffd completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15f78d8288190871d54db0a7f454b completed April 29, 2026, 1:31 a.m.
Created at: April 16, 2026, 8:52 p.m.