Triple
T38542114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leinenkugel’s Lemon Haze IPA |
E924859
|
entity |
| Predicate | citrusFlavorSource |
P188351
|
FINISHED |
| Object | lemon flavoring |
—
|
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: lemon flavoring | Statement: [Leinenkugel’s Lemon Haze IPA, citrusFlavorSource, lemon flavoring]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: citrusFlavorSource Context triple: [Leinenkugel’s Lemon Haze IPA, citrusFlavorSource, lemon flavoring]
-
A.
citrusComponent
Indicates that one entity is a component, ingredient, or constituent part derived from a citrus source in relation to another entity.
-
B.
isCitrusLike
Indicates that one entity has characteristics, qualities, or properties similar to those of citrus fruits.
-
C.
containsCitrusComponent
Indicates that something includes, as part of its composition or contents, one or more components derived from citrus sources.
-
D.
flavorOrigin
chosen
Indicates the source or provenance from which a particular flavor or taste characteristic is derived.
-
E.
containsCitrusJuice
Indicates that one substance or product includes citrus juice as a component or ingredient.
- 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_69f76eadeac081909cdfdd0474cb6765 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcd2eb85e4819088eb5a8fc4d4f668 |
completed | May 7, 2026, 5:59 p.m. |
| PD | Predicate disambiguation | batch_69fcd1f81cbc8190b4fd3bfc3106c1f3 |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.