Triple
T8418383
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speed Stick Antiperspirant |
E198784
|
entity |
| Predicate | regulatoryClass |
P14058
|
FINISHED |
| Object | cosmetic in many markets |
—
|
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: cosmetic in many markets | Statement: [Speed Stick Antiperspirant, regulatoryClass, cosmetic in many markets]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regulatoryClass Context triple: [Speed Stick Antiperspirant, regulatoryClass, cosmetic in many markets]
-
A.
regulatoryType
chosen
Indicates the specific kind or category of regulatory control, rule, or oversight that applies in the given relationship.
-
B.
regulationStatus
Indicates the regulatory condition or compliance state that applies to an entity under relevant rules or laws.
-
C.
regulatorType
Indicates the specific kind or category of regulatory role or authority associated with an entity.
-
D.
regulatoryField
Indicates that one entity operates within, is governed by, or is associated with a particular area or domain of regulation defined by another entity.
-
E.
regulatoryStandard
Indicates that one entity serves as an official rule, guideline, or benchmark that governs, constrains, or evaluates the behavior, quality, or performance of another entity.
- 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_69ca8312d63c8190bf133b676b44a385 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cb84c7d6e48190a2bbde89c5d42af6 |
completed | March 31, 2026, 8:24 a.m. |
| PD | Predicate disambiguation | batch_69cb70d70ea081909c3dc1bd2ec14f85 |
completed | March 31, 2026, 6:59 a.m. |
Created at: March 30, 2026, 6:06 p.m.