Triple
T23104269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Terminal 2 (Xi'an Xianyang International Airport) |
E576118
|
entity |
| Predicate | IATAAirportCodeOfParent |
P2569
|
FINISHED |
| Object | XIY |
—
|
NE NERFINISHED |
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: XIY | Statement: [Terminal 2 (Xi'an Xianyang International Airport), IATAAirportCodeOfParent, XIY]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: XIY Context triple: [Terminal 2 (Xi'an Xianyang International Airport), IATAAirportCodeOfParent, XIY]
-
A.
XIY
chosen
XIY is the IATA airport code for Xi'an Xianyang International Airport, the main air gateway serving Xi'an and the surrounding Shaanxi region in China.
-
B.
IXY
IXY is the IATA airport code for Bhuj Airport in Gujarat, India.
-
C.
YX
YX is the IATA airline designator used by Republic Airways, a major U.S. regional airline operating flights on behalf of larger carriers.
-
D.
YXS
YXS is the IATA airport code for Prince George Airport, a regional air transport hub serving Prince George in central British Columbia, Canada.
-
E.
YXH
YXH is the IATA airport code for Medicine Hat Regional Airport in Alberta, Canada.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e245f4af548190898d434a64a1e774 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18deb702c819099f2e2141706f00e |
completed | April 29, 2026, 4:49 a.m. |
Created at: April 17, 2026, 3:58 p.m.