Triple
T29434724
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | River Jude Phoenix |
E746536
|
entity |
| Predicate | vegetarianOrVegan |
P102865
|
FINISHED |
| Object | vegan |
—
|
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: vegan | Statement: [River Jude Phoenix, vegetarianOrVegan, vegan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vegetarianOrVegan Context triple: [River Jude Phoenix, vegetarianOrVegan, vegan]
-
A.
isVegetarian
Indicates that an entity follows a vegetarian diet, avoiding the consumption of meat and possibly other animal products.
-
B.
isVegan
chosen
Indicates that an entity follows a vegan lifestyle or practice, avoiding the use or consumption of animal products.
-
C.
isPlantBased
Indicates that something is derived from or composed primarily of plants rather than animals or synthetic sources.
-
D.
dietaryOptions
Indicates the types of diets or food-related preferences, restrictions, or choices that are applicable to or offered for an entity.
-
E.
isNonVegetarian
Indicates that an entity consumes or includes meat or animal-based products, and therefore does not follow a vegetarian diet.
- 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_69f0a7a180e48190ae775e40047dbcb5 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f66acbd408819094a2a0d855ab58a1 |
completed | May 2, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69f66339175c819080bd70f0ff7057b1 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 3:15 p.m.