Triple
T13914803
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hainan Airlines |
E334592
|
entity |
| Predicate | headquartersLocation |
P62
|
FINISHED |
| Object | Haikou |
E197372
|
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: Haikou | Statement: [Hainan Airlines, headquartersLocation, Haikou]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Haikou Context triple: [Hainan Airlines, headquartersLocation, Haikou]
-
A.
Haikou
chosen
Haikou is the capital and largest city of China’s Hainan Province, known as a key port, commercial hub, and tropical coastal destination.
-
B.
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.
-
C.
Wanning
Wanning is a county-level coastal city in southeastern Hainan, China, known for its tropical climate, beaches, and surf-friendly bays.
-
D.
Hangtou
Hangtou is a town in Shanghai, China, known as the southern terminus of the Shanghai Metro’s Line 18.
-
E.
Boao
Boao is a coastal town in Hainan, China, best known for hosting the annual Boao Forum for Asia, a major international economic and political conference.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de27260ae08190be45b4b15898e365 |
completed | April 14, 2026, 11:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7c72a345481908f8552bca7bb1a5a |
completed | May 3, 2026, 10:07 p.m. |
Created at: April 9, 2026, 10:16 p.m.