Triple
T4313184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Detroit QLine |
E94121
|
entity |
| Predicate | owner |
P347
|
FINISHED |
| Object |
M-1 Rail
M-1 Rail is the nonprofit organization that developed and oversees Detroit’s QLine streetcar system along Woodward Avenue.
|
E429314
|
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: M-1 Rail | Statement: [Detroit QLine, owner, M-1 Rail]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: M-1 Rail Context triple: [Detroit QLine, owner, M-1 Rail]
-
A.
MARC Train
MARC Train is a commuter rail service operating in Maryland and the surrounding region, connecting cities such as Washington, D.C., Baltimore, and Martinsburg.
-
B.
O-Train
The O-Train is Ottawa’s urban rail transit system, providing light rail service across key corridors of Canada’s capital city.
-
C.
First Rail
First Rail is the rail division of FirstGroup, operating passenger train services and related rail transport operations in the United Kingdom.
-
D.
Länsimetro
Länsimetro is a major westward extension of the Helsinki Metro that connects central Helsinki with the neighboring city of Espoo through a series of new underground stations.
-
E.
AeroTrain
AeroTrain is an automated underground people mover system that transports passengers between terminals at Washington Dulles International Airport.
- 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: M-1 Rail Triple: [Detroit QLine, owner, M-1 Rail]
Generated description
M-1 Rail is the nonprofit organization that developed and oversees Detroit’s QLine streetcar system along Woodward Avenue.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: M-1 Rail Target entity description: M-1 Rail is the nonprofit organization that developed and oversees Detroit’s QLine streetcar system along Woodward Avenue.
-
A.
MARC Train
MARC Train is a commuter rail service operating in Maryland and the surrounding region, connecting cities such as Washington, D.C., Baltimore, and Martinsburg.
-
B.
O-Train
The O-Train is Ottawa’s urban rail transit system, providing light rail service across key corridors of Canada’s capital city.
-
C.
First Rail
First Rail is the rail division of FirstGroup, operating passenger train services and related rail transport operations in the United Kingdom.
-
D.
Länsimetro
Länsimetro is a major westward extension of the Helsinki Metro that connects central Helsinki with the neighboring city of Espoo through a series of new underground stations.
-
E.
AeroTrain
AeroTrain is an automated underground people mover system that transports passengers between terminals at Washington Dulles International Airport.
- 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_69b3451886588190a3dd1305ea7c58dc |
completed | March 12, 2026, 10:58 p.m. |
| NER | Named-entity recognition | batch_69b350f319c08190bb40a9fc5933728d |
completed | March 12, 2026, 11:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5c75f30f48190ab030d635bd334af |
completed | March 14, 2026, 8:38 p.m. |
| NEDg | Description generation | batch_69b5c7d12d408190957f40fe4c9d7ab3 |
completed | March 14, 2026, 8:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b5c890dfa48190af458943224ad2e2 |
completed | March 14, 2026, 8:44 p.m. |
Created at: March 12, 2026, 11:12 p.m.