Triple
T31642956
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Forest Glen station |
E807505
|
entity |
| Predicate | followingStationOnRedLineTowardGlenmont |
P78989
|
FINISHED |
| Object | Silver Spring station |
—
|
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: Silver Spring station | Statement: [Forest Glen station, followingStationOnRedLineTowardGlenmont, Silver Spring station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: followingStationOnRedLineTowardGlenmont Context triple: [Forest Glen station, followingStationOnRedLineTowardGlenmont, Silver Spring station]
-
A.
followingStationOnRedLine
chosen
Indicates that one station is the next station immediately following another station along the Red Line route.
-
B.
followingStationOnRedLineTowardAshmont
Indicates that one station is the next stop after another when traveling on the Red Line in the direction toward Ashmont.
-
C.
followingStationOnBlueLine
Indicates that one station is the next consecutive stop after another station on the Blue Line route.
-
D.
precedingStationOnRedLine
Indicates that one station is immediately before another station along the route of the Red Line.
-
E.
followingStationOnGreenLine
Indicates that one station is the next stop after another station along the Green Line route.
- 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_69f348d9ce58819093ea2da83cbeeec1 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69fd9ff026a48190bfec33deeb3b2c43 |
completed | May 8, 2026, 8:33 a.m. |
| PD | Predicate disambiguation | batch_69fd97d805bc8190ba12f429d3ad04c7 |
completed | May 8, 2026, 7:59 a.m. |
Created at: April 30, 2026, 10:50 p.m.