Triple
T34706340
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Moqueca capixaba |
E1000515
|
entity |
| Predicate | typicallyExcludesIngredient |
P164905
|
FINISHED |
| Object | palm oil |
—
|
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: palm oil | Statement: [Moqueca capixaba, typicallyExcludesIngredient, palm oil]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicallyExcludesIngredient Context triple: [Moqueca capixaba, typicallyExcludesIngredient, palm oil]
-
A.
avoidsIngredient
chosen
Indicates that one entity deliberately does not use, consume, or include a specified ingredient.
-
B.
notableIngredientRestrictionInUS
Indicates that a product or item contains an ingredient that is subject to a notable restriction, limitation, or prohibition within the United States.
-
C.
sometimesExcludes
Indicates that one entity occasionally omits, leaves out, or does not include another entity under certain conditions or at certain times.
-
D.
excludesProduct
Indicates that one entity explicitly omits, disallows, or does not apply to a specified product within its scope or set.
-
E.
excludedFrom
Indicates that one entity is deliberately not included within the scope, membership, or applicability of another entity or set.
- 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_69f76dab937881909c86f1b9ad50445f |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 3:59 p.m.