Triple
T19658008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA Lowell Line |
E471999
|
entity |
| Predicate | servesCommunity |
P82
|
FINISHED |
| Object | Woburn |
—
|
NE NERFINISHED |
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: Woburn | Statement: [MBTA Lowell Line, servesCommunity, Woburn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Woburn Context triple: [MBTA Lowell Line, servesCommunity, Woburn]
-
A.
Woburn
Woburn is a residential neighbourhood in the eastern part of Toronto, Ontario, known for its diverse community and mix of high-rise apartments and single-family homes.
-
B.
Woburn
Woburn is a historic village in Bedfordshire, England, best known for Woburn Abbey and its associated safari park and estate.
-
C.
Woburn
Woburn is a village in Saint George Parish on the Caribbean island nation of Grenada.
-
D.
Woburn, Massachusetts
chosen
Woburn, Massachusetts is a historic suburban city north of Boston known for its early colonial roots and later prominence in industry and commerce.
-
E.
Haverhill
Haverhill is a market town in Suffolk, England, known for its growing population, light industry, and role as a commuter hub for nearby larger cities.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e641475f408190bd42ef3f8d590719 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:45 p.m.