Triple
T22003829
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New World |
E543399
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Song Ji-hyo
Song Ji-hyo is a South Korean actress and television personality best known internationally for her long-running role on the variety show "Running Man" and appearances in numerous films and dramas.
|
E1549555
|
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: Song Ji-hyo | Statement: [New World, starring, Song Ji-hyo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Song Ji-hyo Context triple: [New World, starring, Song Ji-hyo]
-
A.
Jeong Ji-hyun
Jeong Ji-hyun is a Korean individual whose name is romanized from the Korean name Ji-hyun Jung.
-
B.
Suh Ji-hyun
Suh Ji-hyun is a South Korean individual notable for bearing the Korean surname Suh.
-
C.
Song So-hyun
Song So-hyun is a central character in the South Korean dark fantasy series "Hellbound," whose experiences embody the show's themes of fear, faith, and supernatural judgment.
-
D.
Seol Hye-in
Seol Hye-in is a South Korean actress known for her role in the coming-of-age film "The World of Us."
-
E.
Min Hyo-rin
Min Hyo-rin is a South Korean actress, singer, and model known for her roles in films and television dramas as well as her work in the entertainment industry.
- 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: Song Ji-hyo Triple: [New World, starring, Song Ji-hyo]
Generated description
Song Ji-hyo is a South Korean actress and television personality best known internationally for her long-running role on the variety show "Running Man" and appearances in numerous films and dramas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Song Ji-hyo Target entity description: Song Ji-hyo is a South Korean actress and television personality best known internationally for her long-running role on the variety show "Running Man" and appearances in numerous films and dramas.
-
A.
Jeong Ji-hyun
Jeong Ji-hyun is a Korean individual whose name is romanized from the Korean name Ji-hyun Jung.
-
B.
Suh Ji-hyun
Suh Ji-hyun is a South Korean individual notable for bearing the Korean surname Suh.
-
C.
Song So-hyun
Song So-hyun is a central character in the South Korean dark fantasy series "Hellbound," whose experiences embody the show's themes of fear, faith, and supernatural judgment.
-
D.
Seol Hye-in
Seol Hye-in is a South Korean actress known for her role in the coming-of-age film "The World of Us."
-
E.
Min Hyo-rin
Min Hyo-rin is a South Korean actress, singer, and model known for her roles in films and television dramas as well as her work in the entertainment industry.
- 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_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_6a0b73cd90048190972ae88b6828f84a |
completed | May 18, 2026, 8:17 p.m. |
| NEDg | Description generation | batch_6a0b7ad64f38819086f403627f196573 |
completed | May 18, 2026, 8:47 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b7b1cc47081909f58b3462077c323 |
completed | May 18, 2026, 8:48 p.m. |
Created at: April 16, 2026, 8:20 p.m.