Triple
T9427665
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Red Tour |
E227295
|
entity |
| Predicate | sponsor |
P67
|
FINISHED |
| Object |
Cornetto
Cornetto is a popular global ice cream brand best known for its cone-shaped frozen desserts filled with ice cream, chocolate, and nuts.
|
E800164
|
NE FINISHED |
How this triple was built (4 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: Cornetto | Statement: [The Red Tour, sponsor, Cornetto]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cornetto Context triple: [The Red Tour, sponsor, Cornetto]
-
A.
Crispi
Crispi is an Italian surname most notably associated with Francesco Crispi, a prominent 19th-century Italian statesman and former Prime Minister.
-
B.
Crostini
Crostini is the Linux container system in ChromeOS that allows users to run Linux applications alongside Chrome apps on Chromebooks.
-
C.
Rosaroll
Rosaroll was an Italian Philhellene and military figure known for supporting the Greek War of Independence in the early 19th century.
-
D.
Twinkie
Twinkie is a hustling, street-smart high school student in The Fast and the Furious: Tokyo Drift who introduces the protagonist to Tokyo’s underground drift racing scene.
-
E.
Milano cookies
Milano cookies are a popular line of crisp, oval-shaped sandwich cookies filled with chocolate or other flavored layers, produced by Pepperidge Farm.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Cornetto Triple: [The Red Tour, sponsor, Cornetto]
Generated description
Cornetto is a popular global ice cream brand best known for its cone-shaped frozen desserts filled with ice cream, chocolate, and nuts.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Cornetto Target entity description: Cornetto is a popular global ice cream brand best known for its cone-shaped frozen desserts filled with ice cream, chocolate, and nuts.
-
A.
Crispi
Crispi is an Italian surname most notably associated with Francesco Crispi, a prominent 19th-century Italian statesman and former Prime Minister.
-
B.
Crostini
Crostini is the Linux container system in ChromeOS that allows users to run Linux applications alongside Chrome apps on Chromebooks.
-
C.
Rosaroll
Rosaroll was an Italian Philhellene and military figure known for supporting the Greek War of Independence in the early 19th century.
-
D.
Twinkie
Twinkie is a hustling, street-smart high school student in The Fast and the Furious: Tokyo Drift who introduces the protagonist to Tokyo’s underground drift racing scene.
-
E.
Milano cookies
Milano cookies are a popular line of crisp, oval-shaped sandwich cookies filled with chocolate or other flavored layers, produced by Pepperidge Farm.
- F. None of above. chosen
Provenance (5 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_69ca8436ba308190903e470776d2d893 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd7c91ba1c8190b8331fb1ba58cc61 |
completed | April 1, 2026, 8:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1102f93488190bd1ae232c1e34830 |
completed | April 4, 2026, 1:20 p.m. |
| NEDg | Description generation | batch_69d114597b1481909623039f2f5c7fb8 |
completed | April 4, 2026, 1:38 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d114dbfd0c8190b5e2714a6c246486 |
completed | April 4, 2026, 1:40 p.m. |
Created at: March 30, 2026, 7:49 p.m.