Triple
T17175432
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CTrain |
E416846
|
entity |
| Predicate | hasLine |
P35
|
FINISHED |
| Object |
Red Line
The Red Line is a primary light rail route within Calgary's CTrain public transit system, running along a north-south corridor through key areas of the city.
|
E426995
|
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: Red Line | Statement: [CTrain, hasLine, Red Line]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Red Line Context triple: [CTrain, hasLine, Red Line]
-
A.
Red Line
The Red Line is a primary route of the MetroLink light rail system serving key destinations in the St. Louis metropolitan area.
-
B.
Red Line
Red Line is a song by the American rock band Trans Am, known for their experimental blend of post-rock, electronic, and krautrock influences.
-
C.
Red Line
The Red Line is one of the major corridors of the Delhi Metro rapid transit system, serving numerous densely populated areas in and around Delhi.
-
D.
Red Line
Red Line is one of the main rapid transit corridors of the Hyderabad Metro system in Hyderabad, India.
-
E.
Red Line
The Red Line is a light rail route in the Salt Lake City TRAX system that connects key destinations across the Salt Lake Valley.
- 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: Red Line Triple: [CTrain, hasLine, Red Line]
Generated description
The Red Line is a primary light rail route within Calgary's CTrain public transit system, running along a north-south corridor through key areas of the city.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Red Line Target entity description: The Red Line is a primary light rail route within Calgary's CTrain public transit system, running along a north-south corridor through key areas of the city.
-
A.
Red Line
chosen
The Red Line is one of the primary light rail transit routes in Calgary’s CTrain system, running on a north–south axis through key areas of the city.
-
B.
Red Line
The Red Line is a major light rail route in the Dallas Area Rapid Transit (DART) system serving key corridors across the Dallas–Fort Worth metro area.
-
C.
Red Line
The Red Line is a primary route of Pittsburgh’s light rail system, connecting downtown with several southern neighborhoods and suburbs.
-
D.
Red Line
The Red Line is a light rail route in the Salt Lake City TRAX system that connects key destinations across the Salt Lake Valley.
-
E.
Red Line
The Red Line is one of the main light rail routes of Dublin’s Luas tram system, running east–west across the city and serving key central and suburban areas.
- F. None of above.
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_69d886d5f34c8190b24564dfaa63f3fb |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3fc0cec448190b30466628a2ff23f |
completed | April 18, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a016747a8908190a7ce1408abc70c47 |
completed | May 11, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_6a016838367c8190b5117d5314f71a16 |
completed | May 11, 2026, 5:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0168976af88190a5f839a93538ac6f |
completed | May 11, 2026, 5:26 a.m. |
Created at: April 10, 2026, 5:37 a.m.