Triple
T17601495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mosspark |
E428711
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
MPK
MPK is the National Rail station code for Mosspark railway station in Glasgow, Scotland.
|
E1278322
|
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: MPK | Statement: [Mosspark, hasStationCode, MPK]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MPK Context triple: [Mosspark, hasStationCode, MPK]
-
A.
MPK21
MPK21 is a major office building on Meta’s Menlo Park campus, known for its expansive, park-like rooftop and open-plan workspace designed to foster collaboration.
-
B.
MPS
MPS is a leading German research institute specializing in the study of the Sun and the solar system, operating under the Max Planck Society.
-
C.
MPS
MPS (Metal Performance Shaders) is an Apple framework that provides highly optimized GPU-accelerated compute and graphics shaders for tasks like image processing and machine learning on Apple devices.
-
D.
MPS
MPS is the central government agency responsible for public security, policing, and domestic law enforcement in the People's Republic of China.
-
E.
MPS
MPS is a language workbench and integrated development environment by JetBrains designed for creating and working with domain-specific languages using projectional editing.
- 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: MPK Triple: [Mosspark, hasStationCode, MPK]
Generated description
MPK is the National Rail station code for Mosspark railway station in Glasgow, Scotland.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MPK Target entity description: MPK is the National Rail station code for Mosspark railway station in Glasgow, Scotland.
-
A.
MPK21
MPK21 is a major office building on Meta’s Menlo Park campus, known for its expansive, park-like rooftop and open-plan workspace designed to foster collaboration.
-
B.
MPS
MPS is the central government agency responsible for public security, policing, and domestic law enforcement in the People's Republic of China.
-
C.
MPS
MPS is a leading German research institute specializing in the study of the Sun and the solar system, operating under the Max Planck Society.
-
D.
MPS
MPS is a language workbench and integrated development environment by JetBrains designed for creating and working with domain-specific languages using projectional editing.
-
E.
MPS
MPS (Metal Performance Shaders) is an Apple framework that provides highly optimized GPU-accelerated compute and graphics shaders for tasks like image processing and machine learning on Apple devices.
- 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_69d889e1c6148190ba76241e74688f8b |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e46c48dfc08190ba360e6082cffa87 |
completed | April 19, 2026, 5:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01e81b951c81908969e6d2f952efc4 |
completed | May 11, 2026, 2:30 p.m. |
| NEDg | Description generation | batch_6a01ef0a9fb48190ac9d38f027ceb728 |
completed | May 11, 2026, 3 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01ef87c62c8190b9a3cd936542d7b4 |
completed | May 11, 2026, 3:02 p.m. |
Created at: April 10, 2026, 5:51 a.m.