Triple
T37014908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lacolle, Quebec |
E916049
|
entity |
| Predicate | adjacentUSState |
P68114
|
FINISHED |
| Object | New York |
—
|
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: New York | Statement: [Lacolle, Quebec, adjacentUSState, New York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: adjacentUSState Context triple: [Lacolle, Quebec, adjacentUSState, New York]
-
A.
adjacentProvince
Indicates that two provinces share a common boundary and are directly next to each other geographically.
-
B.
hasNeighboringStateToWest
Indicates that one state is geographically located directly to the west of another state, sharing a common border.
-
C.
nearestMainlandState
Indicates the relationship where a given location is associated with the closest U.S. mainland state in terms of geographic proximity.
-
D.
geographicallyAdjacentTo
chosen
Indicates that two geographic entities share a common boundary or are directly next to each other in space.
-
E.
nearestStateOrTerritory
Indicates that one location is the closest state or territory to another location, typically in terms of geographic distance.
- 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_69f76e920dc48190acb6bb7ebc4dffab |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd32848ea88190a71e6df402bbb30e |
completed | May 8, 2026, 12:47 a.m. |
| PD | Predicate disambiguation | batch_69fd2d7e95588190991d5f21e25155df |
completed | May 8, 2026, 12:25 a.m. |
Created at: May 3, 2026, 4:14 p.m.