Triple
T19410634
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 황동혁 |
E485576
|
entity |
| Predicate | 대표작 |
P4
|
FINISHED |
| Object |
수상한 그녀
수상한 그녀는 황동혁 감독이 연출한, 할머니가 갑자기 20대로 젊어지는 기묘한 사건을 통해 가족애와 노년의 삶을 유쾌하게 그린 한국 코미디 영화이다.
|
E1374097
|
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: 수상한 그녀 | Statement: [황동혁, 대표작, 수상한 그녀]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: 수상한 그녀 Context triple: [황동혁, 대표작, 수상한 그녀]
-
A.
The Golden Girl
The Golden Girl is the nickname of Australian sprinter Betty Cuthbert, a four-time Olympic gold medalist renowned for her dominance in track events during the 1950s and 1960s.
-
B.
The Lady Who Dared
The Lady Who Dared is a 1931 American pre-Code drama film starring silent-era leading lady Billie Dove in one of her notable sound-era roles.
-
C.
Golden Girl
Golden Girl is a 1951 musical biographical film starring Mitzi Gaynor as 19th-century entertainer Lotta Crabtree.
-
D.
Three Women
Three Women is a 1921 Cubist-inspired painting by Fernand Léger that depicts three stylized female figures in a bold, mechanized, and brightly colored composition emblematic of his “machine aesthetic.”
-
E.
Pour elle
Pour elle is a 2008 French thriller film about a man who devises an elaborate plan to break his wrongfully imprisoned wife out of jail.
- 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: 수상한 그녀 Triple: [황동혁, 대표작, 수상한 그녀]
Generated description
수상한 그녀는 황동혁 감독이 연출한, 할머니가 갑자기 20대로 젊어지는 기묘한 사건을 통해 가족애와 노년의 삶을 유쾌하게 그린 한국 코미디 영화이다.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: 수상한 그녀 Target entity description: 수상한 그녀는 황동혁 감독이 연출한, 할머니가 갑자기 20대로 젊어지는 기묘한 사건을 통해 가족애와 노년의 삶을 유쾌하게 그린 한국 코미디 영화이다.
-
A.
The Golden Girl
The Golden Girl is the nickname of Australian sprinter Betty Cuthbert, a four-time Olympic gold medalist renowned for her dominance in track events during the 1950s and 1960s.
-
B.
The Lady Who Dared
The Lady Who Dared is a 1931 American pre-Code drama film starring silent-era leading lady Billie Dove in one of her notable sound-era roles.
-
C.
Golden Girl
Golden Girl is a 1951 musical biographical film starring Mitzi Gaynor as 19th-century entertainer Lotta Crabtree.
-
D.
Three Women
Three Women is a 1921 Cubist-inspired painting by Fernand Léger that depicts three stylized female figures in a bold, mechanized, and brightly colored composition emblematic of his “machine aesthetic.”
-
E.
Pour elle
Pour elle is a 2008 French thriller film about a man who devises an elaborate plan to break his wrongfully imprisoned wife out of jail.
- 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_69d8e8d5162481909db12435d9535c1a |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e62af4cc0c81909056b5e2ee574ab1 |
completed | April 20, 2026, 1:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a072b996ebc81908fe7c4ff930896ba |
completed | May 15, 2026, 2:20 p.m. |
| NEDg | Description generation | batch_6a072eb2d5b08190a0cafb1427cfd16d |
completed | May 15, 2026, 2:33 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a072f6caef48190acb52960ebde9ace |
completed | May 15, 2026, 2:36 p.m. |
Created at: April 10, 2026, 1:37 p.m.