Triple
T11650840
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Reckitt Benckiser |
E276898
|
entity |
| Predicate | hasBrand |
P1500
|
FINISHED |
| Object | Gaviscon |
E938969
|
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: Gaviscon | Statement: [Reckitt Benckiser, hasBrand, Gaviscon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gaviscon Context triple: [Reckitt Benckiser, hasBrand, Gaviscon]
-
A.
Gaviscon
chosen
Gaviscon is an over-the-counter antacid and reflux relief medication commonly used to treat heartburn and indigestion.
-
B.
Pepto-Bismol
Pepto-Bismol is an over-the-counter medication commonly used to relieve digestive issues such as nausea, heartburn, indigestion, upset stomach, and diarrhea.
-
C.
Strepsils
Strepsils is a popular brand of medicated throat lozenges used to relieve sore throat and mouth infections.
-
D.
Bromo-Seltzer
Bromo-Seltzer is an American over-the-counter antacid and pain relief effervescent medicine that was widely popular in the early 20th century.
-
E.
Läkerol
Läkerol is a well-known Scandinavian brand of sugar-free pastilles and throat lozenges, recognized for its wide range of flavors and long-standing presence in Nordic confectionery.
- 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_69d6aafbb3c081908a9cdb4ecb8d981d |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a2cea9308190a13f7dd995ea07a4 |
completed | April 10, 2026, 7:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ef138faf4c81908043c71550048d75 |
completed | April 27, 2026, 7:43 a.m. |
Created at: April 8, 2026, 9:39 p.m.