Triple
T7406988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | RKPK |
E170895
|
entity |
| Predicate | hasICAOCode |
P419
|
FINISHED |
| Object | RKPK |
E170895
|
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: RKPK | Statement: [RKPK, hasICAOCode, RKPK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: RKPK Context triple: [RKPK, hasICAOCode, RKPK]
-
A.
RKPK
chosen
RKPK is the ICAO airport code for Gimhae International Airport, serving the Busan region in South Korea.
-
B.
RKP
RKP is the Swedish abbreviation for the Swedish People’s Party of Finland, a liberal-centrist political party representing the Swedish-speaking minority in Finland.
-
C.
RK
RK is the commonly used abbreviation for the Riigikogu, the unicameral national parliament of Estonia.
-
D.
RK
RK is the vehicle registration code used for the town of Ružomberok in northern Slovakia.
-
E.
RKKA
RKKA is the Russian abbreviation for the Workers' and Peasants' Red Army, the Soviet Union's military force from the Russian Civil War through World War II.
- 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_69c68a6010108190925e5284de022660 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f298f2388190afc944c9bc78749a |
completed | March 27, 2026, 9:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8111adbf48190a04df3cec1017b39 |
completed | March 28, 2026, 5:34 p.m. |
Created at: March 27, 2026, 3:10 p.m.