Triple

T22004154
Position Surface form Disambiguated ID Type / Status
Subject Sandglass E543404 entity
Predicate hasCastMember P2308 FINISHED
Object Kim Ji-young (actress)
Kim Ji-young is a South Korean actress best known for her supporting roles in numerous television dramas and films since the 1990s.
E1668059 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: Kim Ji-young (actress) | Statement: [Sandglass, hasCastMember, Kim Ji-young (actress)]
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: Kim Ji-young (actress)
Triple: [Sandglass, hasCastMember, Kim Ji-young (actress)]
Generated description
Kim Ji-young is a South Korean actress best known for her supporting roles in numerous television dramas and films since the 1990s.

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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1276cab5c8190ac1236fde7e0394a completed April 28, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a105ca8a5248190a6f30bfab3aaec80 completed May 22, 2026, 1:39 p.m.
NEDg Description generation batch_6a105e52d9fc8190b22dd25b9cec720b completed May 22, 2026, 1:46 p.m.
NED2 Entity disambiguation (via description) batch_6a105f44a8408190b02fe5f557ea43c1 completed May 22, 2026, 1:51 p.m.
Created at: April 16, 2026, 8:20 p.m.