Triple
T10796366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kai Tak Airport |
E254717
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | HKG |
E8492
|
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: HKG | Statement: [Kai Tak Airport, IATAcode, HKG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: HKG Context triple: [Kai Tak Airport, IATAcode, HKG]
-
A.
Hong Kong, China
chosen
Hong Kong, China is a major global financial and trading hub and a Special Administrative Region of China located on the southern coast of the country.
-
B.
Kowloon
Kowloon is a densely populated urban area of Hong Kong known for its vibrant street life, markets, and skyline facing Victoria Harbour.
-
C.
Port of Hong Kong
The Port of Hong Kong is one of the world’s busiest and most important deep-water container ports, serving as a major international hub for trade and shipping in East Asia.
-
D.
HK
HK is a renowned German defense manufacturer best known for designing and producing small arms such as pistols, rifles, and submachine guns used by military and law enforcement worldwide.
-
E.
HK
HK is the vehicle registration code used for the Czech city of Hradec Králové.
- 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_69d6aa61c15c8190a1839550c56e75e1 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d73332dbfc8190904434846957b618 |
completed | April 9, 2026, 5:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69de84f1fdfc8190a31a13ae434e56c1 |
completed | April 14, 2026, 6:18 p.m. |
Created at: April 8, 2026, 9:17 p.m.