Triple
T2869944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Peter Gatien |
E63534
|
entity |
| Predicate | deportation |
P32330
|
FINISHED |
| Object | was deported from the United States to Canada |
—
|
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: was deported from the United States to Canada | Statement: [Peter Gatien, deportation, was deported from the United States to Canada]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deportation Context triple: [Peter Gatien, deportation, was deported from the United States to Canada]
-
A.
majorDeportation
Indicates that an entity was subjected to a large-scale, often forced, removal or expulsion from a country or region.
-
B.
deportedUnder
Indicates that an entity was deported in accordance with, or by authority of, a specific law, policy, program, or legal provision.
-
C.
deportedBy
Indicates that an entity was expelled or removed from a country or territory by a specific authority, agent, or organization.
-
D.
deportedTo
Indicates that an authority forcibly removed a person from one place or country and sent them to another specified destination.
-
E.
deportedFrom
chosen
Indicates that an authority has expelled an entity from a particular place or country, forcing their departure from that location.
- 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_69ab4c42fb8c8190b36e161d47c03b81 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abdfe15ff081908dd1dad62c292b2b |
completed | March 7, 2026, 8:20 a.m. |
| PD | Predicate disambiguation | batch_69abdd142e4c8190b424cb0c5ff40d04 |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 10:02 p.m.