Triple
T5786570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tramlink |
E128281
|
entity |
| Predicate | depot |
P14646
|
FINISHED |
| Object |
Therapia Lane depot
Therapia Lane depot is the main maintenance and stabling facility for London’s Tramlink light rail network in south London.
|
E549231
|
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: Therapia Lane depot | Statement: [Tramlink, depot, Therapia Lane depot]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Therapia Lane depot Context triple: [Tramlink, depot, Therapia Lane depot]
-
A.
Nopo Depot
Nopo Depot is a maintenance and storage facility serving the Busan Metro system in Busan, South Korea.
-
B.
Vastral Depot
Vastral Depot is a major maintenance and operations facility serving the Ahmedabad Metro system in Ahmedabad, India.
-
C.
Nicklin Way
Nicklin Way is a major arterial road on Queensland’s Sunshine Coast that connects coastal suburbs such as Mooloolaba with other key regional centres.
-
D.
Terminus Place
Terminus Place is a busy public square and transport interchange area located directly outside London Victoria railway station in central London.
-
E.
Fountain Place
Fountain Place is a distinctive, prism-shaped modernist skyscraper in Dallas known for its striking green glass façade and surrounding water features.
- 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: Therapia Lane depot Triple: [Tramlink, depot, Therapia Lane depot]
Generated description
Therapia Lane depot is the main maintenance and stabling facility for London’s Tramlink light rail network in south London.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Therapia Lane depot Target entity description: Therapia Lane depot is the main maintenance and stabling facility for London’s Tramlink light rail network in south London.
-
A.
Nopo Depot
Nopo Depot is a maintenance and storage facility serving the Busan Metro system in Busan, South Korea.
-
B.
Vastral Depot
Vastral Depot is a major maintenance and operations facility serving the Ahmedabad Metro system in Ahmedabad, India.
-
C.
Nicklin Way
Nicklin Way is a major arterial road on Queensland’s Sunshine Coast that connects coastal suburbs such as Mooloolaba with other key regional centres.
-
D.
Terminus Place
Terminus Place is a busy public square and transport interchange area located directly outside London Victoria railway station in central London.
-
E.
Fountain Place
Fountain Place is a distinctive, prism-shaped modernist skyscraper in Dallas known for its striking green glass façade and surrounding water features.
- 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_69c0084450048190bc647b649a05136b |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02a1c29d48190af36cc855bb491dd |
completed | March 22, 2026, 5:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0981a002c8190ac8ed7407a80919c |
completed | March 23, 2026, 1:32 a.m. |
| NEDg | Description generation | batch_69c0989f7e58819098175e6eaacdb9ee |
completed | March 23, 2026, 1:34 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c09cf3220481908c52b519e8495fff |
completed | March 23, 2026, 1:52 a.m. |
Created at: March 22, 2026, 3:51 p.m.