Triple
T7923915
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michelob |
E184011
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Michelob Ultra Pure Gold |
E184011
|
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: Michelob Ultra Pure Gold | Statement: [Michelob, hasVariant, Michelob Ultra Pure Gold]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michelob Ultra Pure Gold Context triple: [Michelob, hasVariant, Michelob Ultra Pure Gold]
-
A.
Michelob
chosen
Michelob is a brand of American beer known for its lagers and light beers, brewed and marketed by Anheuser-Busch.
-
B.
Miller Lite
Miller Lite is a popular American light beer brand known for its lower calorie content and wide availability.
-
C.
Dos Equis Lager Especial
Dos Equis Lager Especial is a popular Mexican pale lager beer known for its light, crisp taste and wide international distribution.
-
D.
Corona Hard Seltzer
Corona Hard Seltzer is a flavored, low-calorie alcoholic seltzer beverage produced under the Corona brand as part of the ready-to-drink hard seltzer market.
-
E.
Bud Light
Bud Light is a popular American light lager beer known for its mild flavor, low calorie content, and wide availability across the United States.
- 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_69ca828fe7bc819090f52c88dcd72183 |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3aac02bc8190b13fc354a4fa91d3 |
completed | March 31, 2026, 3:08 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccec781ac88190b52305beaa213415 |
completed | April 1, 2026, 9:59 a.m. |
Created at: March 30, 2026, 5:06 p.m.