Triple
T21716682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jefferson Notch Road |
E536047
|
entity |
| Predicate | accessesSide |
P86049
|
FINISHED |
| Object | west side of Presidential Range |
—
|
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: west side of Presidential Range | Statement: [Jefferson Notch Road, accessesSide, west side of Presidential Range]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessesSide Context triple: [Jefferson Notch Road, accessesSide, west side of Presidential Range]
-
A.
onSide
chosen
Indicates that one entity is positioned along or adjacent to the side of another entity.
-
B.
accessedThrough
Indicates that one entity is reached, used, or obtained by means of another entity that serves as an intermediary channel, tool, or pathway.
-
C.
accessDirection
Indicates the direction or orientation from which access to something is obtained or permitted.
-
D.
accessesPass
Indicates that one entity uses or is granted a pass (such as a credential, ticket, or authorization token) to gain entry to or make use of another entity.
-
E.
sideEngagementOf
Indicates a relationship where one entity is engaged with or attached to the side of 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_69e0c46c6dd88190a595375fa6ebd701 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69efd96ab4c88190b76f4a6b7c855039 |
completed | April 27, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69e6969725bc81908e7ad19619ba2688 |
completed | April 20, 2026, 9:11 p.m. |
Created at: April 16, 2026, 6:47 p.m.