Triple
T7968014
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guangzhou Baiyun International Airport |
E185253
|
entity |
| Predicate | hasICAOCode |
P419
|
FINISHED |
| Object | ZGGG |
E185254
|
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: ZGGG | Statement: [Guangzhou Baiyun International Airport, hasICAOCode, ZGGG]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ZGGG Context triple: [Guangzhou Baiyun International Airport, hasICAOCode, ZGGG]
-
A.
ZGGG
chosen
ZGGG is the ICAO airport code for Guangzhou Baiyun International Airport, a major aviation hub serving Guangzhou in southern China.
-
B.
ZGHA
ZGHA is the ICAO airport code for Changsha Huanghua International Airport, a major air transport hub serving Changsha and the Hunan province in China.
-
C.
ZG
ZG is the vehicle registration code used on license plates for the city of Zagreb, the capital of Croatia.
-
D.
GZT
GZT is the IATA airport code for Oğuzeli Airport serving Gaziantep in southeastern Turkey.
-
E.
ZPPP
ZPPP is the ICAO airport code for Kunming Changshui International Airport, a major aviation hub in Yunnan Province, China.
- 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_69ca8297699481909b75a405f01e03af |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3bd06ee081908c5080003fb7b8f7 |
completed | March 31, 2026, 3:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cbe0a334e08190ae67a9ca7b51a128 |
completed | March 31, 2026, 2:56 p.m. |
Created at: March 30, 2026, 5:13 p.m.