Triple
T18943106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nashua River Rail Trail |
E463437
|
entity |
| Predicate | usesFormerCorridorOf |
P61930
|
FINISHED |
| Object | railroad |
—
|
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: railroad | Statement: [Nashua River Rail Trail, usesFormerCorridorOf, railroad]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesFormerCorridorOf Context triple: [Nashua River Rail Trail, usesFormerCorridorOf, railroad]
-
A.
formerUseOfCorridor
chosen
Indicates that a corridor was previously used for a particular purpose or function, but is no longer used in that way.
-
B.
formerNameOfCorridor
Indicates that one corridor previously had a different name, which is now the current name of another corridor.
-
C.
followedCorridor
Indicates that an entity moved along and stayed within the path of a corridor from one point to another.
-
D.
hasCorridor
Indicates that one entity includes, is connected by, or provides access through a corridor to another entity.
-
E.
inCorridor
Indicates that one entity is located within or inside a corridor relative to another spatial context or reference.
- 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_69d8dcfec90481909e926be9767e5779 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d3ed847c8190a911a61673608a5c |
completed | April 20, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69e4a2efec5c8190840704016bf547a1 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 11:59 a.m.