Triple
T29502660
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Velveeta |
E748415
|
entity |
| Predicate | isShelfStableBeforeOpening |
P166976
|
FINISHED |
| Object | yes (for some formats) |
—
|
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: yes (for some formats) | Statement: [Velveeta, isShelfStableBeforeOpening, yes (for some formats)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isShelfStableBeforeOpening Context triple: [Velveeta, isShelfStableBeforeOpening, yes (for some formats)]
-
A.
isPerishable
Indicates that an entity is subject to decay, spoilage, or loss of usability over time or under certain conditions.
-
B.
isRefrigeratedForSale
Indicates that an item is kept under refrigeration specifically for the purpose of being offered for sale.
-
C.
isUnspoiled
Indicates that something remains in its original, pristine state, unaffected or undamaged by external influences or changes.
-
D.
canBeStoredFor
Indicates that something is suitable or allowed to be kept in storage for a certain duration or under certain conditions.
-
E.
containsPreservatives
Indicates that one entity (typically a product or substance) includes added preservatives within it.
- F. None of above. chosen
Provenance (4 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_69f0bd455a9c8190b40a3e8ea38cf61f |
completed | April 28, 2026, 1:59 p.m. |
| NER | Named-entity recognition | batch_69f66c33d4bc81908ab72b03c1d747c6 |
completed | May 2, 2026, 9:27 p.m. |
| PD | Predicate disambiguation | batch_69f6633ac8a88190ab0cda62bbfcf9b0 |
completed | May 2, 2026, 8:48 p.m. |
| PDg | Predicate description generation | batch_69f6642e676c8190af0e6b1416eed6d2 |
completed | May 2, 2026, 8:53 p.m. |
Created at: April 28, 2026, 4:25 p.m.