Triple
T12451944
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rexona |
E297552
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Rexona Sport |
E297552
|
NE 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: Rexona Sport | Statement: [Rexona, hasVariant, Rexona Sport]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rexona Sport Context triple: [Rexona, hasVariant, Rexona Sport]
-
A.
Rexona
chosen
Rexona is a global deodorant and antiperspirant brand known for its long-lasting sweat and odor protection products.
-
B.
Skoal
Skoal is a leading U.S. smokeless tobacco brand best known for its moist snuff products.
-
C.
Eau de Cologne
Eau de Cologne is a light, citrus-based perfume originating in 18th-century Cologne, Germany, that became one of the earliest and most influential modern fragrances.
-
D.
Febreze
Febreze is a popular household odor-eliminating product line known for its air fresheners and fabric refreshers.
-
E.
Nivea
Nivea is an American R&B singer best known for her early-2000s hits like "Don't Mess with My Man" and collaborations with prominent hip-hop artists.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d6ada166c48190b902972cd2408fa3 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94d9fa5f0819080ca9f6efa212c59 |
completed | April 10, 2026, 7:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6556839908190ac0401d373ad0fa9 |
completed | May 2, 2026, 7:50 p.m. |
Created at: April 8, 2026, 9:56 p.m.