Triple
T14116366
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tide |
E339785
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Persil |
E297563
|
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: Persil | Statement: [Tide, competitor, Persil]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Persil Context triple: [Tide, competitor, Persil]
-
A.
Woolite
Woolite is a well-known brand of gentle laundry detergent designed to clean and protect delicate fabrics and clothing.
-
B.
Persil (in some markets)
chosen
Persil (in some markets) is a well-known laundry detergent brand sold under Unilever in certain regions, recognized for its stain-removal and fabric-care products.
-
C.
Palmolive
Palmolive is a well-known global brand of soaps and personal care products owned by Colgate-Palmolive.
-
D.
Harpic
Harpic is a widely used brand of toilet and bathroom cleaning products known for its powerful disinfecting and stain-removal formulations.
-
E.
Suavitel
Suavitel is a popular fabric softener brand known for its long-lasting fragrances and softening properties, marketed primarily in Latin American and U.S. Hispanic households.
- 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_69d81c6a95b481909e39111e0c1f31ee |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de6010a03c81909f5f160f8d1fa8fa |
completed | April 14, 2026, 3:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fcd0baa328819099511dfa7b9666d3 |
completed | May 7, 2026, 5:49 p.m. |
Created at: April 9, 2026, 10:22 p.m.