Triple
T15916196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hummingbird cake |
E385975
|
entity |
| Predicate | frostingMainIngredient |
P12771
|
FINISHED |
| Object | cream cheese |
—
|
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: cream cheese | Statement: [Hummingbird cake, frostingMainIngredient, cream cheese]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: frostingMainIngredient Context triple: [Hummingbird cake, frostingMainIngredient, cream cheese]
-
A.
ingredientType
Indicates that one entity is classified as a specific type or category of ingredient in relation to another.
-
B.
usesIngredient
chosen
Indicates that one entity employs or incorporates another entity as an ingredient in its composition or creation.
-
C.
sweetenerType
Indicates the specific kind or category of sweetener associated with or used in relation to an entity.
-
D.
hasMainIngredient
Indicates that one entity is the primary or most significant ingredient used to make another entity.
-
E.
typicalFlavor
Indicates that something characteristically has or is associated with a particular flavor.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e172b48b308190bc430b2308cbc75b |
completed | April 16, 2026, 11:37 p.m. |
| PD | Predicate disambiguation | batch_69e142cf5c548190a931f7b58144cd31 |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:52 a.m.