Triple
T18889888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Machynlleth railway station |
E462054
|
entity |
| Predicate | hasStationCode |
P1289
|
FINISHED |
| Object |
MCN
MCN is the National Rail station code for Machynlleth railway station in Powys, Wales.
|
E1348751
|
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: MCN | Statement: [Machynlleth railway station, hasStationCode, MCN]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MCN Context triple: [Machynlleth railway station, hasStationCode, MCN]
-
A.
MCN
MCN is the three-letter IATA airport code for Middle Georgia Regional Airport in Macon, Georgia, United States.
-
B.
KMCN
KMCN is the ICAO airport code for Middle Georgia Regional Airport, a public airport serving the Macon, Georgia area in the United States.
-
C.
MNC
MNC is the three-letter National Rail station code assigned to Markinch railway station in Fife, Scotland.
-
D.
UMGC
UMGC is a large public online university within the University System of Maryland that specializes in flexible, career-focused degree programs for working adults and military-affiliated students.
-
E.
Bron Media Corp
Bron Media Corp is a Canadian entertainment company that serves as the parent organization overseeing Bron Studios’ film and television production activities.
- 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: MCN Triple: [Machynlleth railway station, hasStationCode, MCN]
Generated description
MCN is the National Rail station code for Machynlleth railway station in Powys, Wales.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MCN Target entity description: MCN is the National Rail station code for Machynlleth railway station in Powys, Wales.
-
A.
MCN
MCN is the three-letter IATA airport code for Middle Georgia Regional Airport in Macon, Georgia, United States.
-
B.
KMCN
KMCN is the ICAO airport code for Middle Georgia Regional Airport, a public airport serving the Macon, Georgia area in the United States.
-
C.
MNC
MNC is the three-letter National Rail station code assigned to Markinch railway station in Fife, Scotland.
-
D.
UMGC
UMGC is a large public online university within the University System of Maryland that specializes in flexible, career-focused degree programs for working adults and military-affiliated students.
-
E.
Bron Media Corp
Bron Media Corp is a Canadian entertainment company that serves as the parent organization overseeing Bron Studios’ film and television production activities.
- 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_69d8dcfc3430819095ee6fc0eb4c06a5 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c479f3208190a9d665865c4b630b |
completed | April 20, 2026, 6:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0582b5539881909838ca1e410f22f8 |
completed | May 14, 2026, 8:07 a.m. |
| NEDg | Description generation | batch_6a0587f71ac88190b4abc38418c0347f |
completed | May 14, 2026, 8:29 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0588880e60819084ecf94861278ebf |
completed | May 14, 2026, 8:32 a.m. |
Created at: April 10, 2026, 11:58 a.m.