Triple
T24568274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sturbridge, Massachusetts |
E607854
|
entity |
| Predicate | hasMajorRoadJunction |
P37486
|
FINISHED |
| Object | junction of Interstate 84 and Interstate 90 |
—
|
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: junction of Interstate 84 and Interstate 90 | Statement: [Sturbridge, Massachusetts, hasMajorRoadJunction, junction of Interstate 84 and Interstate 90]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMajorRoadJunction Context triple: [Sturbridge, Massachusetts, hasMajorRoadJunction, junction of Interstate 84 and Interstate 90]
-
A.
isMajorRoadJunction
chosen
Indicates that a location serves as a primary intersection where major roads or highways meet or cross.
-
B.
hasRoadJunctionType
Indicates that a road junction has a specific type or classification (e.g., roundabout, intersection, interchange).
-
C.
isMajorJunctionOnLine
Indicates that a location serves as a primary connecting junction along a particular line or route.
-
D.
isMajorRoadIn
Indicates that a road is classified as a major road within a specified geographic area or jurisdiction.
-
E.
hasMajorCrossing
Indicates that one entity has a significant or primary intersection or crossing with 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_69e2c4cc35a48190990b7571bc086df8 |
completed | April 17, 2026, 11:39 p.m. |
| NER | Named-entity recognition | batch_69f2a9225d9c8190ae92e5540f6c45c2 |
completed | April 30, 2026, 12:58 a.m. |
| PD | Predicate disambiguation | batch_69f2a6b99e7c8190ba7e2dc8729a314a |
completed | April 30, 2026, 12:47 a.m. |
Created at: April 18, 2026, 2:28 a.m.