Triple
T21869472
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Train to Busan |
E539964
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Sang-hwa
Sang-hwa is a tough yet warm-hearted expectant father and one of the key survivors in the South Korean zombie film "Train to Busan."
|
E1508953
|
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: Sang-hwa | Statement: [Train to Busan, mainCharacter, Sang-hwa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sang-hwa Context triple: [Train to Busan, mainCharacter, Sang-hwa]
-
A.
Kun-hee
Kun-hee is the given name of Lee Kun-hee, the influential South Korean businessman who transformed Samsung into a global technology leader.
-
B.
Jinwicheon
Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
-
C.
Seonghwa
Seonghwa was the era name used during the reign of King Seongjong of the Joseon dynasty in Korea, marking a specific period of his rule.
-
D.
Maeng-hee
Maeng-hee is a Korean given name, notably borne by individuals such as businessman Lee Maeng-hee.
-
E.
Gohyeon
Gohyeon is the main urban and administrative center of Geoje, a city located on Geoje Island in South Gyeongsang Province, South Korea.
- 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: Sang-hwa Triple: [Train to Busan, mainCharacter, Sang-hwa]
Generated description
Sang-hwa is a tough yet warm-hearted expectant father and one of the key survivors in the South Korean zombie film "Train to Busan."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sang-hwa Target entity description: Sang-hwa is a tough yet warm-hearted expectant father and one of the key survivors in the South Korean zombie film "Train to Busan."
-
A.
Kun-hee
Kun-hee is the given name of Lee Kun-hee, the influential South Korean businessman who transformed Samsung into a global technology leader.
-
B.
Jinwicheon
Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
-
C.
Seonghwa
Seonghwa was the era name used during the reign of King Seongjong of the Joseon dynasty in Korea, marking a specific period of his rule.
-
D.
Maeng-hee
Maeng-hee is a Korean given name, notably borne by individuals such as businessman Lee Maeng-hee.
-
E.
Gohyeon
Gohyeon is the main urban and administrative center of Geoje, a city located on Geoje Island in South Gyeongsang Province, South Korea.
- 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f334362c819094af465ee57b47e6 |
completed | April 28, 2026, 5:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a60d3ae28819099a07bb036c68213 |
completed | May 18, 2026, 12:44 a.m. |
| NEDg | Description generation | batch_6a0a618e55c4819099ab070410e4f1a9 |
completed | May 18, 2026, 12:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a621fe47081908575a17b9895395a |
completed | May 18, 2026, 12:49 a.m. |
Created at: April 16, 2026, 6:57 p.m.