Triple
T19746108
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TrawsCymru |
E474254
|
entity |
| Predicate | hasService |
P182
|
FINISHED |
| Object |
T4
T4 is a TrawsCymru long-distance bus service route operating in Wales as part of the national TrawsCymru network.
|
E1393208
|
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: T4 | Statement: [TrawsCymru, hasService, T4]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: T4 Context triple: [TrawsCymru, hasService, T4]
-
A.
T4
T4 is a light rail/tram line of the Trambesòs network serving the Barcelona metropolitan area.
-
B.
T4
T4 is one of the lines of the Athens tram system, providing urban light-rail service across part of the Athens metropolitan area.
-
C.
T4
T4 is a tram line serving the city of Villeurbanne as part of the Lyon metropolitan public transport network in France.
-
D.
T4
T4 is the large, modern main passenger terminal at Adolfo Suárez Madrid–Barajas Airport in Madrid, Spain, known for its distinctive architecture and extensive international flight operations.
-
E.
T4
T4 is the fourth passenger terminal at Melbourne Airport, serving as one of the airport’s main facilities for domestic and low-cost airline operations.
- 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: T4 Triple: [TrawsCymru, hasService, T4]
Generated description
T4 is a TrawsCymru long-distance bus service route operating in Wales as part of the national TrawsCymru network.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: T4 Target entity description: T4 is a TrawsCymru long-distance bus service route operating in Wales as part of the national TrawsCymru network.
-
A.
T4
T4 is a tram line serving the city of Villeurbanne as part of the Lyon metropolitan public transport network in France.
-
B.
T4
T4 is a light rail/tram line of the Trambesòs network serving the Barcelona metropolitan area.
-
C.
T4
T4 is one of the lines of the Athens tram system, providing urban light-rail service across part of the Athens metropolitan area.
-
D.
T4
T4 is a Sydney Trains suburban rail service that operates along the Eastern Suburbs and Illawarra Line in Sydney, Australia.
-
E.
T4
T4 is a tram line that forms part of the urban light rail network serving the city of Casablanca, Morocco.
- 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_69d8e51940a0819087bd2996f98da668 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6529387ac819094e4d66d630e8b98 |
completed | April 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07b501e7348190bf2b14c98cd7cdb0 |
completed | May 16, 2026, 12:06 a.m. |
| NEDg | Description generation | batch_6a07b60822688190b840b21173c45054 |
completed | May 16, 2026, 12:10 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07b6c9fc8c8190825953f50935833e |
completed | May 16, 2026, 12:14 a.m. |
Created at: April 10, 2026, 1:47 p.m.