Triple
T17266434
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Masan |
E419138
|
entity |
| Predicate | notableLocation |
P3858
|
FINISHED |
| Object |
Komam-ni
Komam-ni is a village in South Korea known for being a key site of fighting during the Korean War’s Battle of Masan.
|
E1261811
|
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: Komam-ni | Statement: [Battle of Masan, notableLocation, Komam-ni]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Komam-ni Context triple: [Battle of Masan, notableLocation, Komam-ni]
-
A.
Haeju
Haeju is a coastal city in southwestern North Korea, historically significant as a regional center and port on the Yellow Sea.
-
B.
Musan
Musan is a mining town in northeastern North Korea known for its large iron ore deposits and proximity to the Chinese border.
-
C.
Chinju
Chinju (often spelled Jinju) is a city in South Gyeongsang Province, South Korea, known for its historic fortress, Namgang Yudeung (Lantern) Festival, and rich cultural heritage.
-
D.
Odaesan
Odaesan is a prominent mountain in South Korea known for its scenic national park, rich biodiversity, and important Buddhist temples such as Woljeongsa.
-
E.
Yachimun
Yachimun is the traditional Okinawan pottery style known for its rustic forms, vivid glazes, and deep roots in Ryukyuan culture and craftsmanship.
- 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: Komam-ni Triple: [Battle of Masan, notableLocation, Komam-ni]
Generated description
Komam-ni is a village in South Korea known for being a key site of fighting during the Korean War’s Battle of Masan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Komam-ni Target entity description: Komam-ni is a village in South Korea known for being a key site of fighting during the Korean War’s Battle of Masan.
-
A.
Haeju
Haeju is a coastal city in southwestern North Korea, historically significant as a regional center and port on the Yellow Sea.
-
B.
Musan
Musan is a mining town in northeastern North Korea known for its large iron ore deposits and proximity to the Chinese border.
-
C.
Chinju
Chinju (often spelled Jinju) is a city in South Gyeongsang Province, South Korea, known for its historic fortress, Namgang Yudeung (Lantern) Festival, and rich cultural heritage.
-
D.
Odaesan
Odaesan is a prominent mountain in South Korea known for its scenic national park, rich biodiversity, and important Buddhist temples such as Woljeongsa.
-
E.
Yachimun
Yachimun is the traditional Okinawan pottery style known for its rustic forms, vivid glazes, and deep roots in Ryukyuan culture and craftsmanship.
- 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_69d886d9ab108190b70edd8d17aa1204 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42f45bf608190bcb48783d0d6fb85 |
completed | April 19, 2026, 1:26 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180ce69d08190aa254f219a572a92 |
completed | May 11, 2026, 7:10 a.m. |
| NEDg | Description generation | batch_6a01850140388190949a5f613cef18c2 |
completed | May 11, 2026, 7:28 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a018563d38c819093df94b96b69cfd5 |
completed | May 11, 2026, 7:29 a.m. |
Created at: April 10, 2026, 5:40 a.m.