Triple
T32818607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Line (Washington Metro) stations |
E839370
|
entity |
| Predicate | serveState |
P199506
|
FINISHED |
| Object | Maryland |
—
|
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: Maryland | Statement: [Red Line (Washington Metro) stations, serveState, Maryland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serveState Context triple: [Red Line (Washington Metro) stations, serveState, Maryland]
-
A.
serviceToState
Indicates a relationship where an entity provides service, assistance, or functional support to a state or governmental body.
-
B.
serveAt
Indicates that one entity provides service, work, or duties at a particular place, organization, or event.
-
C.
hasServingState
Indicates that an entity (such as a food or drink item) is associated with a particular state or condition in which it is served.
-
D.
someServe
Indicates that one entity serves, assists, or performs duties for another entity in some capacity.
-
E.
isServed
Indicates that one entity provides or delivers a service, product, or assistance to another entity.
- F. None of above. chosen
Provenance (4 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_69f3493df9008190a8f5d843dcd77704 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
| PDg | Predicate description generation | batch_69ff3fb151008190bf8a90f9f1c5f0c8 |
completed | May 9, 2026, 2:07 p.m. |
Created at: May 1, 2026, 1:15 a.m.