Triple
T16350159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan Mahmud Badaruddin II International Airport |
E397041
|
entity |
| Predicate | IATAcode |
P418
|
FINISHED |
| Object |
PLM
PLM is the IATA airport code for Sultan Mahmud Badaruddin II International Airport serving Palembang, Indonesia.
|
E1209119
|
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: PLM | Statement: [Sultan Mahmud Badaruddin II International Airport, IATAcode, PLM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: PLM Context triple: [Sultan Mahmud Badaruddin II International Airport, IATAcode, PLM]
-
A.
PLM
PLM is a public university in Manila, Philippines, known for offering affordable, high-quality education primarily to the city’s deserving residents.
-
B.
PDM
PDM is a modern Python package and dependency manager that emphasizes PEP 582 support and a streamlined, pyproject.toml-based workflow.
-
C.
PDM
PDM is the station code for Plandome station on the Long Island Rail Road in New York.
-
D.
PLM main line
The PLM main line is the historic principal railway route of the former Paris–Lyon–Mediterranean (PLM) company, connecting Paris with southeastern France and the Mediterranean coast.
-
E.
Teamcenter
Teamcenter is Siemens' comprehensive product lifecycle management (PLM) software platform used to manage product data, processes, and collaboration across the entire product lifecycle.
- 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: PLM Triple: [Sultan Mahmud Badaruddin II International Airport, IATAcode, PLM]
Generated description
PLM is the IATA airport code for Sultan Mahmud Badaruddin II International Airport serving Palembang, Indonesia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: PLM Target entity description: PLM is the IATA airport code for Sultan Mahmud Badaruddin II International Airport serving Palembang, Indonesia.
-
A.
PLM
PLM is a public university in Manila, Philippines, known for offering affordable, high-quality education primarily to the city’s deserving residents.
-
B.
PDM
PDM is the station code for Plandome station on the Long Island Rail Road in New York.
-
C.
PDM
PDM is a modern Python package and dependency manager that emphasizes PEP 582 support and a streamlined, pyproject.toml-based workflow.
-
D.
PLM main line
The PLM main line is the historic principal railway route of the former Paris–Lyon–Mediterranean (PLM) company, connecting Paris with southeastern France and the Mediterranean coast.
-
E.
Teamcenter
Teamcenter is Siemens' comprehensive product lifecycle management (PLM) software platform used to manage product data, processes, and collaboration across the entire product lifecycle.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2da120ec081909bbf32bd128b2e01 |
completed | April 18, 2026, 1:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002db40e0481908d919f2285e48a23 |
completed | May 10, 2026, 7:03 a.m. |
| NEDg | Description generation | batch_6a003082f0008190aeae2fbbfc3a8acf |
completed | May 10, 2026, 7:15 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a00312a4fc48190b6bd6ad9db71bb4d |
completed | May 10, 2026, 7:18 a.m. |
Created at: April 10, 2026, 5:07 a.m.