Triple
T4977525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marbles (Squid Game) |
E111803
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object |
Ji-yeong
Ji-yeong is a tragic supporting character in the Netflix series "Squid Game," known for her poignant friendship with Kang Sae-byeok and her self-sacrificial choice during the marbles game.
|
E496448
|
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: Ji-yeong | Statement: [Marbles (Squid Game), featuresCharacter, Ji-yeong]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ji-yeong Context triple: [Marbles (Squid Game), featuresCharacter, Ji-yeong]
-
A.
Jihae
Jihae is a South Korean singer, songwriter, and actress known for her role in the National Geographic science-fiction series "Mars."
-
B.
Soyeon
Soyeon is a Korean-born interpreter and the wife of former German Chancellor Gerhard Schröder.
-
C.
Han Mi-nyeo
Han Mi-nyeo is a loud, manipulative, and opportunistic contestant in the South Korean survival drama series "Squid Game," known for her volatile alliances and dramatic personality.
-
D.
Jinwicheon
Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
-
E.
Son Mi-na
Son Mi-na is a South Korean athlete best known for delivering the Olympic Oath on behalf of all competitors at the 1988 Seoul Summer Games.
- 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: Ji-yeong Triple: [Marbles (Squid Game), featuresCharacter, Ji-yeong]
Generated description
Ji-yeong is a tragic supporting character in the Netflix series "Squid Game," known for her poignant friendship with Kang Sae-byeok and her self-sacrificial choice during the marbles game.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ji-yeong Target entity description: Ji-yeong is a tragic supporting character in the Netflix series "Squid Game," known for her poignant friendship with Kang Sae-byeok and her self-sacrificial choice during the marbles game.
-
A.
Jihae
Jihae is a South Korean singer, songwriter, and actress known for her role in the National Geographic science-fiction series "Mars."
-
B.
Soyeon
Soyeon is a Korean-born interpreter and the wife of former German Chancellor Gerhard Schröder.
-
C.
Han Mi-nyeo
Han Mi-nyeo is a loud, manipulative, and opportunistic contestant in the South Korean survival drama series "Squid Game," known for her volatile alliances and dramatic personality.
-
D.
Jinwicheon
Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
-
E.
Son Mi-na
Son Mi-na is a South Korean athlete best known for delivering the Olympic Oath on behalf of all competitors at the 1988 Seoul Summer Games.
- 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_69bd441adc208190b70a033a0741d01e |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd7232bd8c8190b325c9198e8b2fa1 |
completed | March 20, 2026, 4:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bec34a07c0819089953ebcbe9cc3ff |
completed | March 21, 2026, 4:11 p.m. |
| NEDg | Description generation | batch_69bec505a5dc81908f79c1ade107c4ce |
completed | March 21, 2026, 4:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bec654fc4881909bf5458cdafc7ffd |
completed | March 21, 2026, 4:24 p.m. |
Created at: March 20, 2026, 1:33 p.m.