Triple
T10207296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jell-O |
E242231
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Jell-O Instant Pudding |
E242231
|
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: Jell-O Instant Pudding | Statement: [Jell-O, hasVariant, Jell-O Instant Pudding]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jell-O Instant Pudding Context triple: [Jell-O, hasVariant, Jell-O Instant Pudding]
-
A.
Jell-O
chosen
Jell-O is a popular brand of flavored gelatin desserts and related products that became a staple of American cuisine and advertising in the 20th century.
-
B.
Scotchmallow
Scotchmallow is a popular See's Candies confection featuring layers of honey marshmallow and buttery caramel enrobed in rich chocolate.
-
C.
Jell-O Company
Jell-O Company was an American food manufacturer best known for creating and popularizing the iconic Jell-O brand of flavored gelatin desserts.
-
D.
Marmelade
Marmelade is a commune in Haiti’s Artibonite Department, known for its mountainous terrain and agricultural production.
-
E.
Fry's English Delight
Fry's English Delight is a BBC Radio 4 documentary series in which Stephen Fry explores the quirks, history, and evolving nature of the English language.
- 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_69d381ae26c48190985abd0e25ee5d04 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d395f8e2b881909c51f8210f09cd4f |
completed | April 6, 2026, 11:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d6a7e63c588190b239f8bdb13a3f3c |
completed | April 8, 2026, 7:09 p.m. |
Created at: April 6, 2026, 10:55 a.m.