Triple
T17927789
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA Fairmount Line |
E448241
|
entity |
| Predicate | servesNeighborhood |
P82
|
FINISHED |
| Object | Dorchester |
E73521
|
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: Dorchester | Statement: [MBTA Fairmount Line, servesNeighborhood, Dorchester]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorchester Context triple: [MBTA Fairmount Line, servesNeighborhood, Dorchester]
-
A.
Dorchester
Dorchester is a historic market town in Dorset, England, known as the county town and closely associated with the life and works of novelist Thomas Hardy.
-
B.
Dorchester
chosen
Dorchester is one of the earliest English settlements in New England, now a historic neighborhood of Boston, Massachusetts.
-
C.
Roxbury
Roxbury is one of the earliest English-settled neighborhoods of present-day Boston, historically significant as a colonial town in what became Massachusetts.
-
D.
Roxbury
Roxbury is a small town located in Dane County, Wisconsin, known for its rural character and proximity to the Madison metropolitan area.
-
E.
Charlestown
Charlestown is an electoral district in the New South Wales Legislative Assembly, representing part of the Newcastle region in Australia.
- 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_69d8b9f79d14819095540856928f0e25 |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e4a5505af88190aa7a5cfee0baa3a4 |
completed | April 19, 2026, 9:50 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a032136546c81909556406f96f8c04b |
completed | May 12, 2026, 12:46 p.m. |
Created at: April 10, 2026, 10:20 a.m.