Triple
T90926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lunenburg |
E1826
|
entity |
| Predicate | hasProximityTo |
P2064
|
FINISHED |
| Object | commuter rail service to Boston area |
—
|
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: commuter rail service to Boston area | Statement: [Lunenburg, hasProximityTo, commuter rail service to Boston area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasProximityTo Context triple: [Lunenburg, hasProximityTo, commuter rail service to Boston area]
-
A.
near
Indicates that one entity is located at a short distance from another entity in space or position.
-
B.
hasAtGradeCrossingNearby
Indicates that one entity (typically a location or segment) has a nearby at-grade crossing where two transportation paths intersect at the same level.
-
C.
nearbyFeature
chosen
Indicates that one entity is located close to or in the immediate vicinity of another entity.
-
D.
locatedBetween
Indicates that one entity is positioned spatially between two other reference entities.
-
E.
accessibleFrom
Indicates that one entity can be reached, entered, or used starting from another entity, typically without obstruction.
- 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_69a24d1a97dc819094e6c021fe9b05a7 |
completed | Feb. 28, 2026, 2:04 a.m. |
| NER | Named-entity recognition | batch_69a24feef1b08190bb9525f71cce053e |
completed | Feb. 28, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69a24eb82d408190b0f9c786152e8e4c |
completed | Feb. 28, 2026, 2:11 a.m. |
Created at: Feb. 28, 2026, 2:07 a.m.