Triple
T15877282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | CTA Yellow Line |
E384981
|
entity |
| Predicate | maintenanceFacility |
P105
|
FINISHED |
| Object | Howard Yard |
E382465
|
NE FINISHED |
How this triple was built (2 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: Howard Yard | Statement: [CTA Yellow Line, maintenanceFacility, Howard Yard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Howard Yard Context triple: [CTA Yellow Line, maintenanceFacility, Howard Yard]
-
A.
Howard Yard
chosen
Howard Yard is a Chicago Transit Authority rail yard that serves as a major storage and maintenance facility for trains on the city's 'L' system.
-
B.
Greenwood Yard
Greenwood Yard is a major maintenance and storage facility serving Toronto's subway system.
-
C.
Edgemere
Edgemere is a coastal neighborhood in the Rockaway Peninsula of Queens, New York City, known for its Atlantic shoreline and residential communities.
-
D.
Masthouse Terrace
Masthouse Terrace is a river bus pier in London served by Thames Clippers services along the River Thames.
-
E.
Haven Green
Haven Green is a well-known public green space and focal point near Ealing Broadway in the London Borough of Ealing.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e155fec9d4819081efea504e1e3952 |
completed | April 16, 2026, 9:34 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa950a890819092bc1e8895034593 |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:51 a.m.