Triple
T16390955
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queenstown Airport |
E398048
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object | ZQN |
E577430
|
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: ZQN | Statement: [Queenstown Airport, IATAcode, ZQN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ZQN Context triple: [Queenstown Airport, IATAcode, ZQN]
-
A.
ZQN
chosen
ZQN is the IATA airport code for Queenstown Airport, the main air gateway to the resort town of Queenstown in New Zealand.
-
B.
QZ
QZ is the IATA airline designator used for AirAsia Indonesia, a low-cost carrier based in Indonesia.
-
C.
GZQ
GZQ is the station code used to identify Guangzhou Railway Station, a major rail transport hub in Guangzhou, China.
-
D.
ZSJN
ZSJN is the ICAO airport code for Jinan Yaoqiang International Airport, the main commercial airport serving Jinan in Shandong Province, China.
-
E.
ZWN
ZWN is a former currency code used to denote an early version of the Zimbabwean dollar in international financial and foreign exchange contexts.
- 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_69d87f2880b48190ae1a9673a3bbef80 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e326425c8081908cacffcfa8c7386b |
completed | April 18, 2026, 6:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00357167b881909a5182537ef973ce |
completed | May 10, 2026, 7:36 a.m. |
Created at: April 10, 2026, 5:08 a.m.