Triple
T8075015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mario Montez |
E188468
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object |
Mario Banana
Mario Banana is a film featuring the underground drag performer and Warhol superstar Mario Montez.
|
E710255
|
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: Mario Banana | Statement: [Mario Montez, appearedIn, Mario Banana]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mario Banana Context triple: [Mario Montez, appearedIn, Mario Banana]
-
A.
Funky Kong
Funky Kong is a laid-back, sunglasses-wearing member of the Kong family in the Donkey Kong video game series, known for running transportation and item shops that help players on their adventures.
-
B.
Yoshi
Yoshi is a friendly, dinosaur-like character from Nintendo’s Mario franchise, known for his long tongue, egg-throwing abilities, and frequent role as Mario’s companion and steed.
-
C.
Mário
Mário is a masculine given name of Latin origin, widely used in Portuguese- and Italian-speaking countries.
-
D.
Mario Runco Jr.
Mario Runco Jr. is a former NASA astronaut and U.S. Navy officer who flew on multiple Space Shuttle missions in the 1990s.
-
E.
Diddy Kong
Diddy Kong is a small, agile monkey from Nintendo's Donkey Kong series, best known as Donkey Kong's sidekick and a playable hero in various platforming and racing games.
- 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: Mario Banana Triple: [Mario Montez, appearedIn, Mario Banana]
Generated description
Mario Banana is a film featuring the underground drag performer and Warhol superstar Mario Montez.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mario Banana Target entity description: Mario Banana is a film featuring the underground drag performer and Warhol superstar Mario Montez.
-
A.
Funky Kong
Funky Kong is a laid-back, sunglasses-wearing member of the Kong family in the Donkey Kong video game series, known for running transportation and item shops that help players on their adventures.
-
B.
Yoshi
Yoshi is a friendly, dinosaur-like character from Nintendo’s Mario franchise, known for his long tongue, egg-throwing abilities, and frequent role as Mario’s companion and steed.
-
C.
Mário
Mário is a masculine given name of Latin origin, widely used in Portuguese- and Italian-speaking countries.
-
D.
Mario Runco Jr.
Mario Runco Jr. is a former NASA astronaut and U.S. Navy officer who flew on multiple Space Shuttle missions in the 1990s.
-
E.
Diddy Kong
Diddy Kong is a small, agile monkey from Nintendo's Donkey Kong series, best known as Donkey Kong's sidekick and a playable hero in various platforming and racing games.
- 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_69ca82b50c708190863f661d438e68df |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb404c513c8190af54d6d6b6d1a81d |
completed | March 31, 2026, 3:32 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63f000308190a55379f8bf67f0cd |
completed | April 1, 2026, 12:16 a.m. |
| NEDg | Description generation | batch_69cc68634dc88190bc9b9e0598929d4d |
completed | April 1, 2026, 12:35 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc6946aa5481908d682957b818a3e9 |
completed | April 1, 2026, 12:39 a.m. |
Created at: March 30, 2026, 5:27 p.m.