Triple
T6284473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBC |
E140863
|
entity |
| Predicate | majorChannel |
P45103
|
FINISHED |
| Object |
MBC FM4U
MBC FM4U is a popular South Korean radio station operated by Munhwa Broadcasting Corporation, known for its contemporary music programming and entertainment shows.
|
E140863
|
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: MBC FM4U | Statement: [MBC, majorChannel, MBC FM4U]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MBC FM4U Context triple: [MBC, majorChannel, MBC FM4U]
-
A.
MBC
MBC is a major South Korean television network known for broadcasting a wide range of entertainment, news, and cultural programs domestically and internationally.
-
B.
MBK
MBK is the station code for Muswellbrook railway station in New South Wales, Australia.
-
C.
MBN
MBN is a U.S.-government-funded media organization that operates Arabic-language television, radio, and digital news services targeting audiences in the Middle East and North Africa.
-
D.
UniMi
UniMi is the commonly used abbreviation for the University of Milan, a major public research university in Milan, Italy.
-
E.
KSMF
KSMF is the ICAO airport code for Sacramento International Airport, a major commercial airport serving California’s capital 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: MBC FM4U Triple: [MBC, majorChannel, MBC FM4U]
Generated description
MBC FM4U is a popular South Korean radio station operated by Munhwa Broadcasting Corporation, known for its contemporary music programming and entertainment shows.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MBC FM4U Target entity description: MBC FM4U is a popular South Korean radio station operated by Munhwa Broadcasting Corporation, known for its contemporary music programming and entertainment shows.
-
A.
MBC
chosen
MBC is a major South Korean television network known for broadcasting a wide range of entertainment, news, and cultural programs domestically and internationally.
-
B.
MBK
MBK is the station code for Muswellbrook railway station in New South Wales, Australia.
-
C.
MBN
MBN is a U.S.-government-funded media organization that operates Arabic-language television, radio, and digital news services targeting audiences in the Middle East and North Africa.
-
D.
UniMi
UniMi is the commonly used abbreviation for the University of Milan, a major public research university in Milan, Italy.
-
E.
KSMF
KSMF is the ICAO airport code for Sacramento International Airport, a major commercial airport serving California’s capital region.
- F. None of above.
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_69c008cd17c8819082b82d3fbeb68047 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063fc906481908283c6c50a212515 |
completed | March 22, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c5196864788190934e7c66d450dcf1 |
completed | March 26, 2026, 11:32 a.m. |
| NEDg | Description generation | batch_69c51e9932cc8190bce03a28097a2ddc |
completed | March 26, 2026, 11:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c51f1689dc8190bbd38cd7a5425224 |
completed | March 26, 2026, 11:57 a.m. |
Created at: March 22, 2026, 4:26 p.m.