Triple
T7622554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fitchburg Line stations |
E172534
|
entity |
| Predicate | connectTo |
P845
|
FINISHED |
| Object | MBTA subway at North Station |
—
|
LITERAL 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: MBTA subway at North Station | Statement: [Fitchburg Line stations, connectTo, MBTA subway at North Station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectTo Context triple: [Fitchburg Line stations, connectTo, MBTA subway at North Station]
-
A.
connectionTo
Indicates a relationship in which one entity is linked, associated, or otherwise related to another entity.
-
B.
connectsTo
chosen
Indicates a relationship where one entity is linked or joined to another, allowing interaction, communication, or transfer between them.
-
C.
connectsUnder
Indicates that one entity forms a connection to another entity by passing beneath or under it.
-
D.
connectsWithin
Indicates that one entity establishes a connection or link between elements that lie inside the bounds or scope of another entity.
-
E.
connectsPartOf
Indicates a relationship where one entity serves to link or join a component to the larger whole of which that component is a part.
- F. None of above.
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_69c699506b308190826894dab1d9ea86 |
completed | March 27, 2026, 2:50 p.m. |
| NER | Named-entity recognition | batch_69c6fe73ff7c8190ab1218d97b37416d |
completed | March 27, 2026, 10:02 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e725a88190b1f05dd224f7f4f2 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:56 p.m.