Triple
T2163254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toronto subway |
E46847
|
entity |
| Predicate | depot |
P14646
|
FINISHED |
| Object |
Greenwood Yard
Greenwood Yard is a major maintenance and storage facility serving Toronto's subway system.
|
E239027
|
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: Greenwood Yard | Statement: [Toronto subway, depot, Greenwood Yard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Greenwood Yard Context triple: [Toronto subway, depot, Greenwood Yard]
-
A.
Aldridge Gardens
Aldridge Gardens is a public botanical garden and event venue in Hoover, Alabama, known for its landscaped grounds, lake, and ornamental hydrangeas.
-
B.
Ashburton Grove
Ashburton Grove is the area in Holloway, North London, that became best known as the site on which Arsenal Football Club’s Emirates Stadium was built.
-
C.
Meriden Green
Meriden Green is a central urban park and community gathering space in downtown Meriden, Connecticut, featuring open green areas, walking paths, and event venues.
-
D.
Courtland Park
Courtland Park is a public recreational park located in Reidsville, North Carolina.
-
E.
Academy Gardens
Academy Gardens is a residential neighborhood in the Northeast section of Philadelphia, Pennsylvania, known for its post–World War II housing and proximity to major city thoroughfares.
- 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: Greenwood Yard Triple: [Toronto subway, depot, Greenwood Yard]
Generated description
Greenwood Yard is a major maintenance and storage facility serving Toronto's subway system.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Greenwood Yard Target entity description: Greenwood Yard is a major maintenance and storage facility serving Toronto's subway system.
-
A.
Aldridge Gardens
Aldridge Gardens is a public botanical garden and event venue in Hoover, Alabama, known for its landscaped grounds, lake, and ornamental hydrangeas.
-
B.
Ashburton Grove
Ashburton Grove is the area in Holloway, North London, that became best known as the site on which Arsenal Football Club’s Emirates Stadium was built.
-
C.
Meriden Green
Meriden Green is a central urban park and community gathering space in downtown Meriden, Connecticut, featuring open green areas, walking paths, and event venues.
-
D.
Courtland Park
Courtland Park is a public recreational park located in Reidsville, North Carolina.
-
E.
Academy Gardens
Academy Gardens is a residential neighborhood in the Northeast section of Philadelphia, Pennsylvania, known for its post–World War II housing and proximity to major city thoroughfares.
- 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_69a88a184cbc8190877791f6552c2484 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abbe8d105c819098371c35c88873dc |
completed | March 7, 2026, 5:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae58ee18ac81909f02e2c87000365b |
completed | March 9, 2026, 5:21 a.m. |
| NEDg | Description generation | batch_69ae597198b88190b0253aa121ed35e1 |
completed | March 9, 2026, 5:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae5a02404c819088acf7c592cb2cae |
completed | March 9, 2026, 5:26 a.m. |
Created at: March 4, 2026, 7:45 p.m.