Triple
T1245870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Baltimore and Ohio Railroad |
E26763
|
entity |
| Predicate | earlyRoute |
P25948
|
FINISHED |
| Object | Baltimore to Ellicott's Mills, Maryland |
—
|
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: Baltimore to Ellicott's Mills, Maryland | Statement: [Baltimore and Ohio Railroad, earlyRoute, Baltimore to Ellicott's Mills, Maryland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: earlyRoute Context triple: [Baltimore and Ohio Railroad, earlyRoute, Baltimore to Ellicott's Mills, Maryland]
-
A.
primaryRoute
Indicates that one route is designated as the main or preferred path among possible alternatives between locations.
-
B.
firstRoutes
Indicates that one route or path is the initial or primary route taken or assigned among a set of possible routes.
-
C.
nextRoute
Indicates that one route directly follows another in a defined sequence or ordering of routes.
-
D.
previousRoute
Indicates that one route directly precedes another in an ordered sequence of routes.
-
E.
route
Indicates that one entity serves as a path or course used to travel or move between locations associated with 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_69a4948689d08190b3a4a3f388c02148 |
completed | March 1, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69a4bf65c41c8190b4c65e015d1264c0 |
completed | March 1, 2026, 10:36 p.m. |
| PD | Predicate disambiguation | batch_69a4bb696a38819095845c84f0241287 |
completed | March 1, 2026, 10:19 p.m. |
| PDg | Predicate description generation | batch_69a4bce611ec819092cb13d354d0903e |
completed | March 1, 2026, 10:25 p.m. |
Created at: March 1, 2026, 7:47 p.m.