Triple

T22837505
Position Surface form Disambiguated ID Type / Status
Subject Beyond Evil E565985 entity
Predicate alsoKnownAs P39 FINISHED
Object Gwimul
Gwimul is the Korean title of the acclaimed 2021 South Korean psychological crime thriller drama series "Beyond Evil."
E1557637 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: Gwimul | Statement: [Beyond Evil, alsoKnownAs, Gwimul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gwimul
Context triple: [Beyond Evil, alsoKnownAs, Gwimul]
  • A. Nam-ku
    Nam-ku is the McCune–Reischauer romanization of Nam District, an administrative district in the city of Busan, South Korea.
  • B. Hwaeom
    Hwaeom is a major school of East Asian Mahayana Buddhism, rooted in the Avatamsaka (Flower Garland) Sutra and known for its doctrine of the interpenetration and mutual containment of all phenomena.
  • C. Jinheung
    Jinheung is the era name associated with King Jinheung of Silla, under which his reign and its historical events are recorded.
  • D. Hwanung
    Hwanung is a heavenly prince in Korean mythology who descends from the sky to found a sacred city and becomes the father of Dangun, the legendary founder of Gojoseon.
  • E. Gugyeol
    Gugyeol is a traditional Korean annotation system used to aid the reading and interpretation of Classical Chinese texts by marking Korean grammatical cues.
  • 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: Gwimul
Triple: [Beyond Evil, alsoKnownAs, Gwimul]
Generated description
Gwimul is the Korean title of the acclaimed 2021 South Korean psychological crime thriller drama series "Beyond Evil."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gwimul
Target entity description: Gwimul is the Korean title of the acclaimed 2021 South Korean psychological crime thriller drama series "Beyond Evil."
  • A. Nam-ku
    Nam-ku is the McCune–Reischauer romanization of Nam District, an administrative district in the city of Busan, South Korea.
  • B. Hwaeom
    Hwaeom is a major school of East Asian Mahayana Buddhism, rooted in the Avatamsaka (Flower Garland) Sutra and known for its doctrine of the interpenetration and mutual containment of all phenomena.
  • C. Jinheung
    Jinheung is the era name associated with King Jinheung of Silla, under which his reign and its historical events are recorded.
  • D. Hwanung
    Hwanung is a heavenly prince in Korean mythology who descends from the sky to found a sacred city and becomes the father of Dangun, the legendary founder of Gojoseon.
  • E. Gugyeol
    Gugyeol is a traditional Korean annotation system used to aid the reading and interpretation of Classical Chinese texts by marking Korean grammatical cues.
  • 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_69e245869e188190a196584f36e682da completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17e303cec81909c5c118dc8c93354 completed April 29, 2026, 3:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ba7b1c6c08190ad3c599ef993c9d0 completed May 18, 2026, 11:58 p.m.
NEDg Description generation batch_6a0ba8666f608190b512aa4c8442f6c1 completed May 19, 2026, 12:01 a.m.
NED2 Entity disambiguation (via description) batch_6a0baa4decf881909774facad2cae93d completed May 19, 2026, 12:09 a.m.
Created at: April 17, 2026, 3:35 p.m.