Triple
T22918460
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doritos |
E568792
|
entity |
| Predicate | collaboratedWith |
P435
|
FINISHED |
| Object | Taco Bell |
—
|
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: Taco Bell | Statement: [Doritos, collaboratedWith, Taco Bell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taco Bell Context triple: [Doritos, collaboratedWith, Taco Bell]
-
A.
Taco Bell
chosen
Taco Bell is a major American fast-food chain known for its Mexican-inspired menu items such as tacos, burritos, and quesadillas.
-
B.
Tacobel Canon
Tacobel Canon is a musical work recognized as part of the classical repertoire.
-
C.
Chipotle Mexican Grill
Chipotle Mexican Grill is a popular American fast-casual restaurant chain known for its customizable burritos, bowls, and tacos made with fresh ingredients.
-
D.
Taco Bell Chihuahua
The Taco Bell Chihuahua was a popular late-1990s advertising character—a small Chihuahua dog known for its catchphrase “¡Yo quiero Taco Bell!” in commercials for the fast-food chain.
-
E.
Carl's Jr.
Carl's Jr. is an American fast-food restaurant chain known for its charbroiled burgers and often provocative advertising campaigns.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1807b254c8190bb84596dcacaa35e |
completed | April 29, 2026, 3:52 a.m. |
Created at: April 17, 2026, 3:42 p.m.