Triple
T22504052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saatchi & Saatchi |
E556343
|
entity |
| Predicate | hasClient |
P734
|
FINISHED |
| Object | Kellogg's |
—
|
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: Kellogg's | Statement: [Saatchi & Saatchi, hasClient, Kellogg's]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kellogg's Context triple: [Saatchi & Saatchi, hasClient, Kellogg's]
-
A.
Kellogg Company
chosen
Kellogg Company is a major American multinational food manufacturing company best known for its breakfast cereals and convenience foods.
-
B.
Postum Cereal Company
Postum Cereal Company was an American food manufacturer best known as the predecessor to General Foods and for producing popular breakfast cereals and the Postum coffee substitute.
-
C.
General Mills
General Mills is a major American multinational food company known for producing popular brands of cereals, snacks, and packaged foods.
-
D.
Quaker Oats
Quaker Oats is a well-known American food brand specializing in oatmeal and other grain-based products.
-
E.
Pillsbury Company
Pillsbury Company is a major American food company best known for its packaged baking products, refrigerated doughs, and iconic Doughboy mascot.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e555edc81909ca803587dafd747 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15d5ac5808190a66f9111c350f4dc |
completed | April 29, 2026, 1:22 a.m. |
Created at: April 16, 2026, 8:50 p.m.