Triple
T7996597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Busan–Jinhae Free Economic Zone |
E186141
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
BJFEZ
BJFEZ is a designated free economic zone in South Korea focused on attracting foreign investment and fostering high-tech and logistics industries around the Busan–Jinhae area.
|
E702277
|
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: BJFEZ | Statement: [Busan–Jinhae Free Economic Zone, abbreviation, BJFEZ]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: BJFEZ Context triple: [Busan–Jinhae Free Economic Zone, abbreviation, BJFEZ]
-
A.
JEF
JEF is the IATA airport code for Jefferson City Memorial Airport, a public airport serving Jefferson City, Missouri.
-
B.
BZE
BZE is the IATA airport code for Philip S. W. Goldson International Airport, the main international gateway serving Belize.
-
C.
EZJ
EZJ is the London Stock Exchange ticker symbol for easyJet, a major British low-cost airline.
-
D.
FZ
FZ is the vehicle registration code assigned to cars registered in the city of Zielona Góra in western Poland.
-
E.
FZ
FZ is the IATA airline designator assigned to flydubai, the low-cost carrier based in Dubai, United Arab Emirates.
- 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: BJFEZ Triple: [Busan–Jinhae Free Economic Zone, abbreviation, BJFEZ]
Generated description
BJFEZ is a designated free economic zone in South Korea focused on attracting foreign investment and fostering high-tech and logistics industries around the Busan–Jinhae area.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: BJFEZ Target entity description: BJFEZ is a designated free economic zone in South Korea focused on attracting foreign investment and fostering high-tech and logistics industries around the Busan–Jinhae area.
-
A.
JEF
JEF is the IATA airport code for Jefferson City Memorial Airport, a public airport serving Jefferson City, Missouri.
-
B.
BZE
BZE is the IATA airport code for Philip S. W. Goldson International Airport, the main international gateway serving Belize.
-
C.
EZJ
EZJ is the London Stock Exchange ticker symbol for easyJet, a major British low-cost airline.
-
D.
FZ
FZ is the vehicle registration code assigned to cars registered in the city of Zielona Góra in western Poland.
-
E.
FZ
FZ is the IATA airline designator assigned to flydubai, the low-cost carrier based in Dubai, United Arab Emirates.
- 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_69ca829c6c308190ab05b43d234c52b2 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3c97968481908d261b3f0bd6b8e6 |
completed | March 31, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe10d5eb081909f257390094de442 |
completed | March 31, 2026, 2:58 p.m. |
| NEDg | Description generation | batch_69cbe4888800819080eb11c9b7b7e28f |
completed | March 31, 2026, 3:13 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc1175c8a481909b29d3b850ad9084 |
completed | March 31, 2026, 6:24 p.m. |
Created at: March 30, 2026, 5:17 p.m.