Triple
T38386378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | US 2 |
E899590
|
entity |
| Predicate | roughlyParallelTo |
P158086
|
FINISHED |
| Object | Canadian border |
—
|
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: Canadian border | Statement: [US 2, roughlyParallelTo, Canadian border]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roughlyParallelTo Context triple: [US 2, roughlyParallelTo, Canadian border]
-
A.
isPartiallyParallelTo
chosen
Indicates that two entities are aligned in roughly the same direction but not exactly parallel, sharing only a partial or approximate parallel relationship.
-
B.
orientedParallelTo
Indicates that one entity is parallel to another with a specified or consistent direction or orientation.
-
C.
isParallelWithRespectTo
Indicates that two or more entities maintain a constant separation and never intersect within a specified reference or coordinate system.
-
D.
nowLargelyParalleledBy
Indicates that something has been mostly matched or replicated by something else in function, scope, or effect.
-
E.
parallel
Indicates that two or more entities maintain a constant separation and direction without intersecting or converging.
- 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_69f76e5c9b808190b486523f5c2f817d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcd1499e2c81909bafd84dc4810f45 |
completed | May 7, 2026, 5:52 p.m. |
| PD | Predicate disambiguation | batch_69fcccf024ec819086383ffbb6cfc036 |
completed | May 7, 2026, 5:33 p.m. |
Created at: May 3, 2026, 4:31 p.m.