Triple
T9590161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Middle Korean |
E231395
|
entity |
| Predicate | writingSystem |
P454
|
FINISHED |
| Object |
Hyangchal
Hyangchal is an ancient Korean writing system that used Chinese characters phonetically and semantically to transcribe native Korean, especially in early vernacular poetry.
|
E808103
|
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: Hyangchal | Statement: [Middle Korean, writingSystem, Hyangchal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hyangchal Context triple: [Middle Korean, writingSystem, Hyangchal]
-
A.
Yeongdodaegyo
Yeongdodaegyo is a bascule bridge in Busan, South Korea, known as the city’s first mainland–island bridge and a local historical landmark.
-
B.
Tanaeang
Tanaeang is a village settlement located on the atoll of Tabiteuea in the island nation of Kiribati in the central Pacific Ocean.
-
C.
Sinseongbong
Sinseongbong is a prominent mountain peak located within the Gyeryongsan mountain range in South Korea.
-
D.
Gwan-eum
Gwan-eum is the Korean name for Guanyin, the bodhisattva of compassion widely revered in East Asian Buddhism.
-
E.
Dangsandong
Dangsandong is a neighborhood in Seoul, South Korea, known as a residential and commercial area within the city's southwestern region.
- 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: Hyangchal Triple: [Middle Korean, writingSystem, Hyangchal]
Generated description
Hyangchal is an ancient Korean writing system that used Chinese characters phonetically and semantically to transcribe native Korean, especially in early vernacular poetry.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hyangchal Target entity description: Hyangchal is an ancient Korean writing system that used Chinese characters phonetically and semantically to transcribe native Korean, especially in early vernacular poetry.
-
A.
Yeongdodaegyo
Yeongdodaegyo is a bascule bridge in Busan, South Korea, known as the city’s first mainland–island bridge and a local historical landmark.
-
B.
Tanaeang
Tanaeang is a village settlement located on the atoll of Tabiteuea in the island nation of Kiribati in the central Pacific Ocean.
-
C.
Sinseongbong
Sinseongbong is a prominent mountain peak located within the Gyeryongsan mountain range in South Korea.
-
D.
Gwan-eum
Gwan-eum is the Korean name for Guanyin, the bodhisattva of compassion widely revered in East Asian Buddhism.
-
E.
Dangsandong
Dangsandong is a neighborhood in Seoul, South Korea, known as a residential and commercial area within the city's southwestern region.
- 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_69ca8482884481908eccdfdf64d6fbf7 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd99f32e688190bb13bccfa5031f16 |
completed | April 1, 2026, 10:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d161880adc819090a9be75ba2a1642 |
completed | April 4, 2026, 7:07 p.m. |
| NEDg | Description generation | batch_69d161d569b88190a3d77bbe752e0c86 |
completed | April 4, 2026, 7:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d162476bf481909a87057e4fd1dc11 |
completed | April 4, 2026, 7:11 p.m. |
Created at: March 30, 2026, 8:06 p.m.