Triple
T25668673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Packards Corner station |
E643598
|
entity |
| Predicate | nearIntersectionWith |
P49266
|
FINISHED |
| Object | Brighton Avenue |
—
|
NE NERFINISHED |
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: Brighton Avenue | Statement: [Packards Corner station, nearIntersectionWith, Brighton Avenue]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearIntersectionWith Context triple: [Packards Corner station, nearIntersectionWith, Brighton Avenue]
-
A.
nearestPointTo
Indicates the point that is closest in distance to a given reference point or object among a set of candidates.
-
B.
hasNearbyCrossingPoint
chosen
Indicates that one location has a crossing point (such as a bridge, crosswalk, or intersection) situated close to it.
-
C.
nearestPass
Indicates that one entity is the closest in distance or proximity to another entity compared to all other possible entities or paths.
-
D.
nearBorderDirection
Indicates that one entity is located close to a border or boundary in a specified directional orientation relative to that border.
-
E.
hasNearbyPoint
Indicates that one entity has at least one other point located within a specified proximity or distance from it.
- 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_69e77e7e45648190a068ed3faa8016ea |
completed | April 21, 2026, 1:41 p.m. |
| NER | Named-entity recognition | batch_69f5fb3096ec8190bebd54d74fa8e1ba |
completed | May 2, 2026, 1:25 p.m. |
| PD | Predicate disambiguation | batch_69f4807f8680819098a524158d049c63 |
completed | May 1, 2026, 10:29 a.m. |
Created at: April 21, 2026, 7:09 p.m.