Triple
T27715207
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Taylor ham |
E698796
|
entity |
| Predicate | foodSafety |
P86304
|
FINISHED |
| Object | must be refrigerated |
—
|
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: must be refrigerated | Statement: [Taylor ham, foodSafety, must be refrigerated]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foodSafety Context triple: [Taylor ham, foodSafety, must be refrigerated]
-
A.
foodSafetyPractice
chosen
Indicates actions or procedures followed to prevent food contamination and ensure it is safe for consumption.
-
B.
foodProcessing
Indicates a process in which raw or semi-processed food materials are transformed, prepared, or treated to produce consumable food products.
-
C.
foodPolicy
Indicates the rules, guidelines, or strategies that govern how food is produced, distributed, sold, or consumed within a given context.
-
D.
mainFoodAffected
Indicates that a primary or central food item is directly impacted or influenced by a specified action or condition.
-
E.
foundInFood
Indicates that a substance, ingredient, or component is present within or contained in a particular food item.
- 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_69ef590f655c81909f93893b3b3219b2 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f635cfa6088190aae92d408c036238 |
completed | May 2, 2026, 5:35 p.m. |
| PD | Predicate disambiguation | batch_69f62c1a92648190835a2c5250d8c758 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 3:04 p.m.