Triple
T7104300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sean Canning |
E165535
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Canning |
E165535
|
NE 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: Canning | Statement: [Sean Canning, familyName, Canning]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Canning Context triple: [Sean Canning, familyName, Canning]
-
A.
Canning
chosen
Canning is an English surname most notably associated with George Canning, a 19th-century British statesman and briefly Prime Minister.
-
B.
Canning
Canning is a town in the South 24 Parganas district of West Bengal, India, known as a gateway to the Sundarbans mangrove forests.
-
C.
FoodSaver
FoodSaver is a consumer brand best known for its home vacuum sealing systems that help preserve and store food for longer periods.
-
D.
Can of Pork
Can of Pork is a 1992 punk rock compilation album featuring various bands from the Lookout Records roster and related artists.
-
E.
Saveur
Saveur is a culinary magazine known for its in-depth exploration of global cuisines, food culture, and travel.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69c6887fcddc8190a5d58908f6dee590 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e58b3f708190bebca7d4c4db40f2 |
completed | March 27, 2026, 8:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7daff33bc8190825078d791ff0b3a |
completed | March 28, 2026, 1:43 p.m. |
Created at: March 27, 2026, 2:42 p.m.