Triple
T781549
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MBTA Green Line D branch |
E16506
|
entity |
| Predicate | openedAsLightRail |
P10389
|
FINISHED |
| Object | 1959 |
—
|
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: 1959 | Statement: [MBTA Green Line D branch, openedAsLightRail, 1959]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: openedAsLightRail Context triple: [MBTA Green Line D branch, openedAsLightRail, 1959]
-
A.
openedAsRailStop
Indicates that an entity began operation or was first established specifically as a railway stop.
-
B.
hasLightRailSystem
Indicates that a place possesses and operates a light rail transit system.
-
C.
openedAsRedLineStation
Indicates that a station began operation specifically as part of the Red Line when it first opened.
-
D.
openedToRailTraffic
Indicates that a rail line, track, or related infrastructure has begun operating and is officially available for use by train traffic.
-
E.
metroLineInaugurated
chosen
Indicates that a metro line was officially opened and began operation on a specific date or during a specific event.
- 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_69a4936ad1fc81908f190208059ccf78 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a4a90365648190ace53b0f0e87aa68 |
completed | March 1, 2026, 9 p.m. |
| PD | Predicate disambiguation | batch_69a4a50bd23081908908235b8ec9201e |
completed | March 1, 2026, 8:43 p.m. |
Created at: March 1, 2026, 7:37 p.m.