Triple
T22400989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korla Airport |
E553757
|
entity |
| Predicate | hasIATACode |
P2569
|
FINISHED |
| Object |
KRL
KRL is the IATA airport code for Korla Airport, a regional airport serving Korla in Xinjiang, China.
|
E1534368
|
NE FINISHED |
How this triple was built (4 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: KRL | Statement: [Korla Airport, hasIATACode, KRL]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: KRL Context triple: [Korla Airport, hasIATACode, KRL]
-
A.
KRL
KRL is a Pakistani nuclear and defense research facility known for its key role in the development of Pakistan’s nuclear weapons program.
-
B.
"KRL"
KRL is the station code for Kraków Lotnisko, the railway station serving Kraków’s John Paul II International Airport in Poland.
-
C.
KRL Commuterline
KRL Commuterline is the electric commuter rail network serving the Greater Jakarta metropolitan area, providing mass transit for millions of daily passengers.
-
D.
Jakarta LRT
Jakarta LRT is a light rail transit system serving parts of the Greater Jakarta metropolitan area in Indonesia, designed to alleviate traffic congestion and improve urban mobility.
-
E.
Jakarta MRT
Jakarta MRT is a rapid transit system serving Indonesia’s capital region, designed to reduce congestion and improve urban mobility through modern, high-capacity rail services.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: KRL Triple: [Korla Airport, hasIATACode, KRL]
Generated description
KRL is the IATA airport code for Korla Airport, a regional airport serving Korla in Xinjiang, China.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: KRL Target entity description: KRL is the IATA airport code for Korla Airport, a regional airport serving Korla in Xinjiang, China.
-
A.
KRL
KRL is a Pakistani nuclear and defense research facility known for its key role in the development of Pakistan’s nuclear weapons program.
-
B.
"KRL"
KRL is the station code for Kraków Lotnisko, the railway station serving Kraków’s John Paul II International Airport in Poland.
-
C.
KRL Commuterline
KRL Commuterline is the electric commuter rail network serving the Greater Jakarta metropolitan area, providing mass transit for millions of daily passengers.
-
D.
Jakarta LRT
Jakarta LRT is a light rail transit system serving parts of the Greater Jakarta metropolitan area in Indonesia, designed to alleviate traffic congestion and improve urban mobility.
-
E.
Jakarta MRT
Jakarta MRT is a rapid transit system serving Indonesia’s capital region, designed to reduce congestion and improve urban mobility through modern, high-capacity rail services.
- F. None of above. chosen
Provenance (5 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_69e11e4da7048190b4387d422a9a0de5 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f158b39c908190a735aa860d733869 |
completed | April 29, 2026, 1:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0ae9cd35648190a37c9814c581749e |
completed | May 18, 2026, 10:28 a.m. |
| NEDg | Description generation | batch_6a0aea9aad5c81908fca5ea2b594effb |
completed | May 18, 2026, 10:31 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0aeb4ce6d48190ac9281afb7b43391 |
completed | May 18, 2026, 10:34 a.m. |
Created at: April 16, 2026, 8:46 p.m.