Triple
T23755750
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fort Totten station (Washington Metro) |
E587109
|
entity |
| Predicate | addedService |
P4097
|
FINISHED |
| Object | Green Line |
—
|
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: Green Line | Statement: [Fort Totten station (Washington Metro), addedService, Green Line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: addedService Context triple: [Fort Totten station (Washington Metro), addedService, Green Line]
-
A.
introducedToService
Indicates that one entity has presented or brought another entity into contact with a particular service for the first time.
-
B.
serviceIntroduced
Indicates that a particular service has been launched, made available, or brought into operation at a certain time or context.
-
C.
addedFor
Indicates that one entity was created, included, or introduced specifically for the benefit, use, or purpose of another entity.
-
D.
addedTo
chosen
Indicates that one entity has been included or incorporated into another entity, typically as a new component, member, or element.
-
E.
serviceWith
Indicates that one entity provides or is associated with a particular service offered to or used by 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_69e2490a0eec81908cdef8a862828d7a |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1bdab86108190becd7f27650082cc |
completed | April 29, 2026, 8:13 a.m. |
| PD | Predicate disambiguation | batch_69f155f79e34819080f9ddb972b34deb |
completed | April 29, 2026, 12:51 a.m. |
Created at: April 17, 2026, 7:14 p.m.