Triple
T3176383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hainan Airlines |
E66474
|
entity |
| Predicate | callsign |
P1565
|
FINISHED |
| Object | HAINAN |
E37179
|
NE FINISHED |
How this triple was built (2 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: HAINAN | Statement: [Hainan Airlines, callsign, HAINAN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HAINAN Context triple: [Hainan Airlines, callsign, HAINAN]
-
A.
Hainan
chosen
Hainan is a tropical island province in southern China known for its beaches, tourism, and status as a major special economic zone.
-
B.
Fujian
Fujian is a coastal province in southeastern China known for its significant role in Chinese migration, distinctive Min culture and dialects, and historic maritime trade.
-
C.
Haikou
Haikou is the capital and largest city of China’s Hainan Province, known as a key port, commercial hub, and tropical coastal destination.
-
D.
Guangdong Province
Guangdong Province is a populous and economically vital coastal region in southern China, known for major cities like Guangzhou and Shenzhen and its role as a manufacturing and trade hub.
-
E.
Sanya
Sanya is a major resort city on the southern coast of China’s Hainan Island, known for its tropical climate and popular beach tourism.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ad8586a34c8190944c63ec11a8de1a |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada69b0bec8190957913b44d876079 |
completed | March 8, 2026, 4:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b24b7076d48190b614e4b48965e0b4 |
completed | March 12, 2026, 5:13 a.m. |
Created at: March 8, 2026, 3:06 p.m.