Triple
T27388251
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Glenmont, Maryland |
E691442
|
entity |
| Predicate | metropolitanRailTerminus |
P26272
|
FINISHED |
| Object | Glenmont 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: Glenmont station | Statement: [Glenmont, Maryland, metropolitanRailTerminus, Glenmont station]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: metropolitanRailTerminus Context triple: [Glenmont, Maryland, metropolitanRailTerminus, Glenmont station]
-
A.
railTerminus
Indicates that a railway line or service ends at a particular station or location, which serves as its final terminus.
-
B.
railLineTerminus
chosen
Indicates that a rail line ends or terminates at the specified location or station.
-
C.
hasLondonUndergroundStation
Indicates that a place or area contains at least one London Underground (Tube) station within its boundaries.
-
D.
railTerminusFor
Indicates that one location serves as the final or terminal rail station or endpoint for a specified rail line or service.
-
E.
subwayStation
Indicates that one entity is a subway station associated with, located in, or serving the other 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_69ef520386788190bc92cfcd97ebb67a |
completed | April 27, 2026, 12:09 p.m. |
| NER | Named-entity recognition | batch_69f62c8d15d48190825465932c36a6c3 |
completed | May 2, 2026, 4:55 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 12:25 p.m.