Triple
T21404488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Severo-Kurilsk Airport |
E527997
|
entity |
| Predicate | hasICAOCode |
P419
|
FINISHED |
| Object | UHSK |
—
|
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: UHSK | Statement: [Severo-Kurilsk Airport, hasICAOCode, UHSK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: UHSK Context triple: [Severo-Kurilsk Airport, hasICAOCode, UHSK]
-
A.
UHSK
chosen
UHSK is the ICAO airport code assigned to Severo-Kurilsk Airport in Russia’s Kuril Islands.
-
B.
HSK
HSK is the vehicle registration code for the Hochsauerlandkreis district in the German state of North Rhine-Westphalia.
-
C.
Gaokao
Gaokao is China’s highly competitive national college entrance examination that largely determines students’ access to universities and future educational opportunities.
-
D.
UHK
UHK is a public university in Hradec Králové, Czech Republic, offering a range of academic programs and research activities across multiple faculties.
-
E.
Hanyu
Hanyu is a Chinese given name shared by various individuals, including notable figures in fields such as acting, sports, and academia.
- 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_69e0b520ee3c8190abddbee7e37e834c |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e8b1ade4188190aca09bbbf2c2db87 |
completed | April 22, 2026, 11:31 a.m. |
Created at: April 16, 2026, 5:31 p.m.