Triple
T23645985
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Democratic Party of Korea |
E584033
|
entity |
| Predicate | hasNotableMember |
P304
|
FINISHED |
| Object |
Park Young-sun
Park Young-sun is a South Korean politician and former journalist who has served as a prominent lawmaker and cabinet minister.
|
E1935148
|
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: Park Young-sun | Statement: [Democratic Party of Korea, hasNotableMember, Park Young-sun]
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: Park Young-sun Triple: [Democratic Party of Korea, hasNotableMember, Park Young-sun]
Generated description
Park Young-sun is a South Korean politician and former journalist who has served as a prominent lawmaker and cabinet minister.
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_69e248fefafc81909656921192f30e80 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b28571bc8190b3f7275068d19320 |
completed | April 29, 2026, 7:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a28c7a394f4819097c064774bc1a5b7 |
completed | June 10, 2026, 2:10 a.m. |
| NEDg | Description generation | batch_6a28c9ad2abc819092e3594cd9dce679 |
completed | June 10, 2026, 2:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a28ca0facb88190acd8987e118ef8fc |
completed | June 10, 2026, 2:21 a.m. |
Created at: April 17, 2026, 6:48 p.m.