Triple
T18906159
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Herbalife Ltd. |
E462467
|
entity |
| Predicate | brandName |
P1500
|
FINISHED |
| Object | Herbalife |
—
|
NE NERFINISHED |
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: Herbalife | Statement: [Herbalife Ltd., brandName, Herbalife]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Herbalife Context triple: [Herbalife Ltd., brandName, Herbalife]
-
A.
Herbalife
chosen
Herbalife is a global multi-level marketing company that sells nutritional supplements and weight-management products.
-
B.
Amway
Amway is a global multi-level marketing company that sells health, beauty, and home care products through a network of independent distributors.
-
C.
Yamamoto Nutrition
Yamamoto Nutrition is a sports nutrition and supplement brand known for formulating products aimed at bodybuilders and high-performance athletes.
-
D.
Grupo Omnilife
Grupo Omnilife is a Mexican multinational company best known for its nutritional supplement business and for owning the popular football club C.D. Guadalajara (Chivas).
-
E.
Nutrilite
Nutrilite is a global dietary supplement and vitamin brand known for its plant-based, organically grown ingredients and is marketed through Amway’s direct-selling network.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c52cc9cc8190ac489d36e51693c8 |
completed | April 20, 2026, 6:18 a.m. |
Created at: April 10, 2026, 11:58 a.m.