Triple

T27155229
Position Surface form Disambiguated ID Type / Status
Subject La casa de papel: Corea E682500 entity
Predicate hasCharacter P2308 FINISHED
Object Inspector Seon Woo-jin
Inspector Seon Woo-jin is a determined and sharp-witted police negotiator in the South Korean adaptation of the heist series "La casa de papel: Corea."
E1756814 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: Inspector Seon Woo-jin | Statement: [La casa de papel: Corea, hasCharacter, Inspector Seon Woo-jin]
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: Inspector Seon Woo-jin
Triple: [La casa de papel: Corea, hasCharacter, Inspector Seon Woo-jin]
Generated description
Inspector Seon Woo-jin is a determined and sharp-witted police negotiator in the South Korean adaptation of the heist series "La casa de papel: Corea."

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_69eefaceb2a08190b9659b7f730629f5 completed April 27, 2026, 5:57 a.m.
NER Named-entity recognition batch_69f625069a00819096cf4b71a69a3563 completed May 2, 2026, 4:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12482d95308190b01fd8e6632905b3 completed May 24, 2026, 12:37 a.m.
NEDg Description generation batch_6a1248bbf1608190a87ffa2885256df7 completed May 24, 2026, 12:39 a.m.
NED2 Entity disambiguation (via description) batch_6a12495a291481909f278a9bd423fea7 completed May 24, 2026, 12:42 a.m.
Created at: April 27, 2026, 9:16 a.m.