Triple
T4201854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gosforth depot |
E86084
|
entity |
| Predicate | hasTypeOfRollingStockServiced |
P1305
|
FINISHED |
| Object |
Tyne and Wear Metro Class 994 units
The Tyne and Wear Metro Class 994 units are electric multiple-unit trains specifically built for and operated on the Tyne and Wear Metro light rail system in North East England.
|
E420769
|
NE FINISHED |
How this triple was built (5 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: Tyne and Wear Metro Class 994 units | Statement: [Gosforth depot, hasTypeOfRollingStockServiced, Tyne and Wear Metro Class 994 units]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tyne and Wear Metro Class 994 units Context triple: [Gosforth depot, hasTypeOfRollingStockServiced, Tyne and Wear Metro Class 994 units]
-
A.
British Rail Class 168
The British Rail Class 168 is a diesel multiple-unit train used primarily by Chiltern Railways for regional and intercity services in the United Kingdom.
-
B.
British Rail Class 323
The British Rail Class 323 is a type of electric multiple unit train widely used on suburban and commuter rail services in the West Midlands and North West England.
-
C.
British Rail Class 172
The British Rail Class 172 is a diesel multiple-unit train used on regional and suburban services in the UK, featuring improved performance, reliability, and passenger comfort over earlier Turbostar units.
-
D.
British Rail Class 332
The British Rail Class 332 is an electric multiple unit train type built in the late 1990s specifically for high-speed, premium passenger services between London Paddington and Heathrow Airport.
-
E.
British Rail Class 387
The British Rail Class 387 is a fleet of modern electric multiple-unit trains used on high-speed commuter and airport services in the UK.
- 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: Tyne and Wear Metro Class 994 units Triple: [Gosforth depot, hasTypeOfRollingStockServiced, Tyne and Wear Metro Class 994 units]
Generated description
The Tyne and Wear Metro Class 994 units are electric multiple-unit trains specifically built for and operated on the Tyne and Wear Metro light rail system in North East England.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tyne and Wear Metro Class 994 units Target entity description: The Tyne and Wear Metro Class 994 units are electric multiple-unit trains specifically built for and operated on the Tyne and Wear Metro light rail system in North East England.
-
A.
British Rail Class 168
The British Rail Class 168 is a diesel multiple-unit train used primarily by Chiltern Railways for regional and intercity services in the United Kingdom.
-
B.
British Rail Class 323
The British Rail Class 323 is a type of electric multiple unit train widely used on suburban and commuter rail services in the West Midlands and North West England.
-
C.
British Rail Class 172
The British Rail Class 172 is a diesel multiple-unit train used on regional and suburban services in the UK, featuring improved performance, reliability, and passenger comfort over earlier Turbostar units.
-
D.
British Rail Class 332
The British Rail Class 332 is an electric multiple unit train type built in the late 1990s specifically for high-speed, premium passenger services between London Paddington and Heathrow Airport.
-
E.
British Rail Class 387
The British Rail Class 387 is a fleet of modern electric multiple-unit trains used on high-speed commuter and airport services in the UK.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTypeOfRollingStockServiced Context triple: [Gosforth depot, hasTypeOfRollingStockServiced, Tyne and Wear Metro Class 994 units]
-
A.
usesRollingStock
Indicates that one entity employs or operates specific rolling stock (such as rail vehicles) in its activities or services.
-
B.
ownedRollingStock
Indicates that one entity possesses or has ownership rights over specific rolling stock (such as trains, railcars, or locomotives).
-
C.
formerRollingStock
Indicates that an entity was previously used as rolling stock (e.g., railway vehicles) but no longer serves in that capacity.
-
D.
introducedRollingStock
Indicates that an entity caused new rolling stock (such as trains or rail vehicles) to be put into service or use.
-
E.
rollingStockType
chosen
Indicates the specific category or type of railway rolling stock associated with an entity (e.g., locomotive, passenger car, freight wagon).
- F. None of above.
Provenance (6 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_69aed93b89f48190a31f6d57c760e42f |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af037da30481908106b27a88d59140 |
completed | March 9, 2026, 5:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b58a173a78819094915f63c8411602 |
completed | March 14, 2026, 4:17 p.m. |
| NEDg | Description generation | batch_69b58e1e7bc08190b75486c74953f609 |
completed | March 14, 2026, 4:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b58e7a208481909056b6fba4597bf4 |
completed | March 14, 2026, 4:36 p.m. |
| PD | Predicate disambiguation | batch_69af01959c4881909eb1adcb3bdadbe6 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:49 p.m.