Triple
T21367123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA Mattapan Line |
E526945
|
entity |
| Predicate | openedAsCurrentService |
P6141
|
FINISHED |
| Object | 1929 |
—
|
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: 1929 | Statement: [MBTA Mattapan Line, openedAsCurrentService, 1929]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openedAsCurrentService Context triple: [MBTA Mattapan Line, openedAsCurrentService, 1929]
-
A.
openedFirstService
Indicates that one entity initiated or conducted the first instance of a particular service for another entity or in a given context.
-
B.
openedForServiceTo
Indicates that one entity has been made available or activated to provide service or functionality to another entity.
-
C.
openedForThroughService
Indicates that an entity has been made accessible or available specifically for use via a through-service connection or route, rather than as a standalone endpoint.
-
D.
openedAsRevenueService
Indicates that an entity was initiated or launched specifically to operate as a revenue-generating service.
-
E.
openedAs
chosen
Indicates that one entity began operating, functioning, or being available to the public under the form, name, or role of another entity.
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee5bae5eb88190be6d9ff4dc03d52b |
completed | April 26, 2026, 6:38 p.m. |
| PD | Predicate disambiguation | batch_69e6162bbfc88190a3e75859941b2638 |
completed | April 20, 2026, 12:03 p.m. |
Created at: April 16, 2026, 5:09 p.m.