Triple
T17207331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan Syarif Kasim II International Airport |
E417633
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object |
PKU
PKU is the IATA airport code for Sultan Syarif Kasim II International Airport serving Pekanbaru in Riau, Indonesia.
|
E1256408
|
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: PKU | Statement: [Sultan Syarif Kasim II International Airport, IATAcode, PKU]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PKU Context triple: [Sultan Syarif Kasim II International Airport, IATAcode, PKU]
-
A.
PKU
PKU is a leading Chinese research university in Beijing renowned for its rigorous academics, influential alumni, and historic campus.
-
B.
MPS II
MPS II, also known as Hunter syndrome, is a rare X-linked lysosomal storage disorder caused by iduronate-2-sulfatase deficiency, leading to progressive multi-organ dysfunction and developmental impairment.
-
C.
Hurler
Hurler is a wooden roller coaster at the Carowinds amusement park known for its high-speed, rough-and-tumble ride experience.
-
D.
Alport
Alport is a small hamlet in Derbyshire, England, situated in the Peak District and known for its picturesque rural setting and historic stone buildings.
-
E.
Krabbé
Krabbé is a Dutch surname most notably associated with actor and director Jeroen Krabbé.
- 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: PKU Triple: [Sultan Syarif Kasim II International Airport, IATAcode, PKU]
Generated description
PKU is the IATA airport code for Sultan Syarif Kasim II International Airport serving Pekanbaru in Riau, Indonesia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: PKU Target entity description: PKU is the IATA airport code for Sultan Syarif Kasim II International Airport serving Pekanbaru in Riau, Indonesia.
-
A.
PKU
PKU is a leading Chinese research university in Beijing renowned for its rigorous academics, influential alumni, and historic campus.
-
B.
MPS II
MPS II, also known as Hunter syndrome, is a rare X-linked lysosomal storage disorder caused by iduronate-2-sulfatase deficiency, leading to progressive multi-organ dysfunction and developmental impairment.
-
C.
Hurler
Hurler is a wooden roller coaster at the Carowinds amusement park known for its high-speed, rough-and-tumble ride experience.
-
D.
Alport
Alport is a small hamlet in Derbyshire, England, situated in the Peak District and known for its picturesque rural setting and historic stone buildings.
-
E.
Krabbé
Krabbé is a Dutch surname most notably associated with actor and director Jeroen Krabbé.
- 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_69d886d6ba8c819093215917b3d01689 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42dc283648190b2c1f957940024aa |
completed | April 19, 2026, 1:20 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a015fe0a28c8190a76b3a356f7e0478 |
completed | May 11, 2026, 4:49 a.m. |
| NEDg | Description generation | batch_6a0161ceed2081908d2efe69c5bc06a0 |
completed | May 11, 2026, 4:57 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0162692420819097b99a71ec470861 |
completed | May 11, 2026, 5 a.m. |
Created at: April 10, 2026, 5:38 a.m.