Triple

T23485775
Position Surface form Disambiguated ID Type / Status
Subject Provisional Government of the Republic of Korea E570528 entity
Predicate leader P981 FINISHED
Object Yi Sang-ryong
Yi Sang-ryong was a Korean independence activist and politician who served as a key leader of the Korean Provisional Government in exile during Japanese colonial rule.
E1746145 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: Yi Sang-ryong | Statement: [Provisional Government of the Republic of Korea, leader, Yi Sang-ryong]
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: Yi Sang-ryong
Triple: [Provisional Government of the Republic of Korea, leader, Yi Sang-ryong]
Generated description
Yi Sang-ryong was a Korean independence activist and politician who served as a key leader of the Korean Provisional Government in exile during Japanese colonial rule.

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_69e245b0b01481908f636939bedd804c completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1a7538a8c8190b7effcc39a3f9787 completed April 29, 2026, 6:38 a.m.
NED1 Entity disambiguation (via context triple) batch_6a121e66e284819093df1feb202cd573 completed May 23, 2026, 9:38 p.m.
NEDg Description generation batch_6a121f2214c88190a68cd83be4196fc5 completed May 23, 2026, 9:41 p.m.
NED2 Entity disambiguation (via description) batch_6a121f96d69081909fa69572c9e3e1f8 completed May 23, 2026, 9:43 p.m.
Created at: April 17, 2026, 6:03 p.m.