Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

{ "The Lion King": ["🦁", "πŸ‘‘", "πŸŒ…", "🌿", "πŸ’"], "The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"], "The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"], "The Matrix": ["πŸ’Š", "πŸ•ΆοΈ", "πŸ–₯️", "πŸ”«", "πŸ€–"], "Casablanca": ["✈️", "🎹", "🍸", "🎰", "πŸ•°οΈ"], "Raiders of the Lost Ark": ["🏺", "🐍", "πŸ—ΊοΈ", "πŸ”", "πŸ’€"], "V for Vendetta": ["🎭", "πŸ’£", "πŸ”ͺ", "πŸ—½", "🌹"], "The Princess Bride": ["βš”οΈ", "πŸ’—", "πŸ΄β€β˜ οΈ", "πŸ§—", "🀺"], "Back to the Future": ["⏰", "πŸš—", "⚑", "🎸", "πŸ›Ή"], "Dune": ["🏜️", "πŸͺ±", "🌎", "βš”οΈ", "πŸš€"] }

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["🦁", "πŸ‘‘", "πŸŒ…", "🌿", "πŸ’"],
"The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"],
"The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"],
"The Matrix": ["πŸ’Š", "πŸ•ΆοΈ", "πŸ–₯️", "πŸ”«", "πŸ€–"],
"Casablanca": ["✈️", "🎹", "🍸", "🎰", "πŸ•°οΈ"],
"Raiders of the Lost Ark": ["🏺", "🐍", "πŸ—ΊοΈ", "πŸ”", "πŸ’€"],
"V for Vendetta": ["🎭", "πŸ’£", "πŸ”ͺ", "πŸ—½", "🌹"],
"The Princess Bride": ["βš”οΈ", "πŸ’—", "πŸ΄β€β˜ οΈ", "πŸ§—", "🀺"],
"Back to the Future": ["⏰", "πŸš—", "⚑", "🎸", "πŸ›Ή"],
"Dune": ["🏜️", "πŸͺ±", "🌎", "βš”οΈ", "πŸš€"]
}

PyFunc

Resulting in output: [['🦁', 'πŸ‘‘', 'πŸŒ…', '🌿', 'πŸ’'], ['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'], ['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'], ['πŸ’Š', 'πŸ•ΆοΈ', 'πŸ–₯️', 'πŸ”«', 'πŸ€–'], ['✈️', '🎹', '🍸', '🎰', 'πŸ•°οΈ'], ['🏺', '🐍', 'πŸ—ΊοΈ', 'πŸ”', 'πŸ’€'], ['🎭', 'πŸ’£', 'πŸ”ͺ', 'πŸ—½', '🌹'], ['βš”οΈ', 'πŸ’—', 'πŸ§—', '🀺'], ['⏰', 'πŸš—', '⚑', '🎸', 'πŸ›Ή'], ['🏜️', 'πŸͺ±', '🌎', 'βš”οΈ', 'πŸš€']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'],
['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'],
['πŸ’Š', 'πŸ•ΆοΈ', 'πŸ–₯️', 'πŸ”«', 'πŸ€–'],
['✈️', '🎹', '🍸', '🎰', 'πŸ•°οΈ'],
['🏺', '🐍', 'πŸ—ΊοΈ', 'πŸ”', 'πŸ’€'],
['🎭', 'πŸ’£', 'πŸ”ͺ', 'πŸ—½', '🌹'],
['βš”οΈ', 'πŸ’—', 'πŸ§—', '🀺'],
['⏰', 'πŸš—', '⚑', '🎸', 'πŸ›Ή'],
['🏜️', 'πŸͺ±', '🌎', 'βš”οΈ', 'πŸš€']]
What are the names of the movie titles?

Output

Here's my attempt to match movie titles to the emoji descriptions you provided: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "Fight Club",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]
These are my best guesses based on the emoji combinations provided. Some movies are more clearly represented than others, but I've tried to match each set of emojis to the most fitting well-known movie title.

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "Fight Club",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

{ "The Lion King": ["🦁", "πŸ‘‘", "πŸŒ…", "πŸ’", "🌿"], "The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"], "The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"], "The Matrix": ["πŸ’Š", "πŸ–₯️", "πŸ‘¨β€πŸ’»", "πŸ•ΆοΈ", "πŸ”«"], "Casablanca": ["✈️", "🎹", "🍸", "🎰", "❀️"], "Raiders of the Lost Ark": ["🏺", "🐍", "πŸ—ΊοΈ", "πŸ”", "πŸ‘¨β€πŸ«"], "V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸŽ†", "πŸ›οΈ"], "The Princess Bride": ["βš”οΈ", "πŸ‘Έ", "πŸ’•", "πŸ΄β€β˜ οΈ", "πŸ§—"], "Back to the Future": ["πŸš—", "⏰", "⚑", "🎸", "πŸ‘¨β€πŸ”¬"], "Dune": ["🏜️", "πŸͺ±", "🌠", "βš”οΈ", "πŸŒ‘"] }

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["🦁", "πŸ‘‘", "πŸŒ…", "πŸ’", "🌿"],
"The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"],
"The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"],
"The Matrix": ["πŸ’Š", "πŸ–₯️", "πŸ‘¨β€πŸ’»", "πŸ•ΆοΈ", "πŸ”«"],
"Casablanca": ["✈️", "🎹", "🍸", "🎰", "❀️"],
"Raiders of the Lost Ark": ["🏺", "🐍", "πŸ—ΊοΈ", "πŸ”", "πŸ‘¨β€πŸ«"],
"V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸŽ†", "πŸ›οΈ"],
"The Princess Bride": ["βš”οΈ", "πŸ‘Έ", "πŸ’•", "πŸ΄β€β˜ οΈ", "πŸ§—"],
"Back to the Future": ["πŸš—", "⏰", "⚑", "🎸", "πŸ‘¨β€πŸ”¬"],
"Dune": ["🏜️", "πŸͺ±", "🌠", "βš”οΈ", "πŸŒ‘"]
}

PyFunc

Resulting in output: [['🦁', 'πŸ‘‘', 'πŸŒ…', 'πŸ’', '🌿'], ['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'], ['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'], ['πŸ’Š', 'πŸ–₯️', 'πŸ•ΆοΈ', 'πŸ”«'], ['✈️', '🎹', '🍸', '🎰', '❀️'], ['🏺', '🐍', 'πŸ—ΊοΈ', 'πŸ”'], ['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸŽ†', 'πŸ›οΈ'], ['βš”οΈ', 'πŸ‘Έ', 'πŸ’•', 'πŸ§—'], ['πŸš—', '⏰', '⚑', '🎸'], ['🏜️', 'πŸͺ±', '🌠', 'βš”οΈ', 'πŸŒ‘']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'],
['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'],
['πŸ’Š', 'πŸ–₯️', 'πŸ•ΆοΈ', 'πŸ”«'],
['✈️', '🎹', '🍸', '🎰', '❀️'],
['🏺', '🐍', 'πŸ—ΊοΈ', 'πŸ”'],
['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸŽ†', 'πŸ›οΈ'],
['βš”οΈ', 'πŸ‘Έ', 'πŸ’•', 'πŸ§—'],
['πŸš—', '⏰', '⚑', '🎸'],
['🏜️', 'πŸͺ±', '🌠', 'βš”οΈ', 'πŸŒ‘']]
What are the names of the movie titles?

Output

Here's my attempt to match movie titles to the given emoji descriptions: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

{ "The Lion King": ["🦁", "πŸ‘‘", "πŸ’", "πŸŒ…", "πŸ—"], "The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"], "The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"], "The Matrix": ["πŸ’»", "πŸ•ΆοΈ", "πŸ”΄", "πŸ”΅", "πŸ₯‹"], "Casablanca": ["✈️", "🎹", "🍸", "🎰", "πŸ•°οΈ"], "Raiders of the Lost Ark": ["🏺", "🐍", "πŸ—ΊοΈ", "πŸ‘¨β€πŸ«", "⚑"], "V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸŽ†", "πŸ”₯"], "The Princess Bride": ["βš”οΈ", "πŸ’‘", "πŸ΄β€β˜ οΈ", "πŸ’ͺ", "🧠"], "Back to the Future": ["⏰", "πŸš—", "⚑", "πŸ›Ή", "🎸"], "Dune": ["🏜️", "πŸ›", "🌠", "βš”οΈ", "πŸŒ‘"] }

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["🦁", "πŸ‘‘", "πŸ’", "πŸŒ…", "πŸ—"],
"The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"],
"The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"],
"The Matrix": ["πŸ’»", "πŸ•ΆοΈ", "πŸ”΄", "πŸ”΅", "πŸ₯‹"],
"Casablanca": ["✈️", "🎹", "🍸", "🎰", "πŸ•°οΈ"],
"Raiders of the Lost Ark": ["🏺", "🐍", "πŸ—ΊοΈ", "πŸ‘¨β€πŸ«", "⚑"],
"V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸŽ†", "πŸ”₯"],
"The Princess Bride": ["βš”οΈ", "πŸ’‘", "πŸ΄β€β˜ οΈ", "πŸ’ͺ", "🧠"],
"Back to the Future": ["⏰", "πŸš—", "⚑", "πŸ›Ή", "🎸"],
"Dune": ["🏜️", "πŸ›", "🌠", "βš”οΈ", "πŸŒ‘"]
}

PyFunc

Resulting in output: [['🦁', 'πŸ‘‘', 'πŸ’', 'πŸŒ…', 'πŸ—'], ['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'], ['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'], ['πŸ’»', 'πŸ•ΆοΈ', 'πŸ”΄', 'πŸ”΅', 'πŸ₯‹'], ['✈️', '🎹', '🍸', '🎰', 'πŸ•°οΈ'], ['🏺', '🐍', 'πŸ—ΊοΈ', '⚑'], ['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸŽ†', 'πŸ”₯'], ['βš”οΈ', 'πŸ’‘', 'πŸ’ͺ', '🧠'], ['⏰', 'πŸš—', '⚑', 'πŸ›Ή', '🎸'], ['🏜️', 'πŸ›', '🌠', 'βš”οΈ', 'πŸŒ‘']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'],
['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'],
['πŸ’»', 'πŸ•ΆοΈ', 'πŸ”΄', 'πŸ”΅', 'πŸ₯‹'],
['✈️', '🎹', '🍸', '🎰', 'πŸ•°οΈ'],
['🏺', '🐍', 'πŸ—ΊοΈ', '⚑'],
['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸŽ†', 'πŸ”₯'],
['βš”οΈ', 'πŸ’‘', 'πŸ’ͺ', '🧠'],
['⏰', 'πŸš—', '⚑', 'πŸ›Ή', '🎸'],
['🏜️', 'πŸ›', '🌠', 'βš”οΈ', 'πŸŒ‘']]
What are the names of the movie titles?

Output

Here's my attempt to match movie titles to the given emoji descriptions: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]
These are my best guesses based on the emoji combinations provided. Some movies are more clearly represented than others, but I've tried to match each set of emojis to the most likely corresponding film title.

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

{ "The Lion King": ["🦁", "πŸ‘‘", "πŸŒ…", "πŸ’", "🌿"], "The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"], "The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"], "The Matrix": ["πŸ’Š", "πŸ‘¨β€πŸ’»", "πŸ•ΆοΈ", "πŸ”«", "πŸ€–"], "Casablanca": ["✈️", "🍸", "🎹", "πŸ’”", "πŸ•°οΈ"], "Raiders of the Lost Ark": ["🏺", "🐍", "πŸ”", "πŸ—ΊοΈ", "πŸ’€"], "V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸ›οΈ", "🌹"], "The Princess Bride": ["βš”οΈ", "πŸ’‘", "πŸ΄β€β˜ οΈ", "πŸ‘¨β€βš•οΈ", "🏰"], "Back to the Future": ["πŸš—", "⏰", "⚑", "🎸", "πŸ‘¨β€πŸ”¬"], "Dune": ["🏜️", "πŸͺ±", "πŸš€", "πŸ‘οΈ", "βš”οΈ"] }

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["🦁", "πŸ‘‘", "πŸŒ…", "πŸ’", "🌿"],
"The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"],
"The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"],
"The Matrix": ["πŸ’Š", "πŸ‘¨β€πŸ’»", "πŸ•ΆοΈ", "πŸ”«", "πŸ€–"],
"Casablanca": ["✈️", "🍸", "🎹", "πŸ’”", "πŸ•°οΈ"],
"Raiders of the Lost Ark": ["🏺", "🐍", "πŸ”", "πŸ—ΊοΈ", "πŸ’€"],
"V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸ›οΈ", "🌹"],
"The Princess Bride": ["βš”οΈ", "πŸ’‘", "πŸ΄β€β˜ οΈ", "πŸ‘¨β€βš•οΈ", "🏰"],
"Back to the Future": ["πŸš—", "⏰", "⚑", "🎸", "πŸ‘¨β€πŸ”¬"],
"Dune": ["🏜️", "πŸͺ±", "πŸš€", "πŸ‘οΈ", "βš”οΈ"]
}

PyFunc

Resulting in output: [['🦁', 'πŸ‘‘', 'πŸŒ…', 'πŸ’', '🌿'], ['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'], ['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'], ['πŸ’Š', 'πŸ•ΆοΈ', 'πŸ”«', 'πŸ€–'], ['✈️', '🍸', '🎹', 'πŸ’”', 'πŸ•°οΈ'], ['🏺', '🐍', 'πŸ”', 'πŸ—ΊοΈ', 'πŸ’€'], ['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸ›οΈ', '🌹'], ['βš”οΈ', 'πŸ’‘', '🏰'], ['πŸš—', '⏰', '⚑', '🎸'], ['🏜️', 'πŸͺ±', 'πŸš€', 'πŸ‘οΈ', 'βš”οΈ']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'],
['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'],
['πŸ’Š', 'πŸ•ΆοΈ', 'πŸ”«', 'πŸ€–'],
['✈️', '🍸', '🎹', 'πŸ’”', 'πŸ•°οΈ'],
['🏺', '🐍', 'πŸ”', 'πŸ—ΊοΈ', 'πŸ’€'],
['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸ›οΈ', '🌹'],
['βš”οΈ', 'πŸ’‘', '🏰'],
['πŸš—', '⏰', '⚑', '🎸'],
['🏜️', 'πŸͺ±', 'πŸš€', 'πŸ‘οΈ', 'βš”οΈ']]
What are the names of the movie titles?

Output

Here's my attempt to match the emoji descriptions to movie titles, presented as a JSON list: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

PyFunc

OK Resulting in output: True

Initial Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

LLM Generation

Query

For each of the following ten movies give at most 5 emoji that would best describe the movie. Give your answer as a JSON array. So If I asked for 

1
you might might answer 
1
2
{"Finding Nemo": ["🐠", "🐟", "🐑", "🐬", "🐳"],
"Toy Story": ["πŸš€", "βš”οΈ,", "πŸ€–", "πŸ‘½", "🌌"]}
. Each emoji must be a single utf8 character. ABSOLUTELY NO ZERO WIDTH JOINING. (So, max(len(emoji) for movie in result.values() for emoji in movie) == 1) Now give me answers for these movies: 
1
Give ONLY a JSON output. Nothing else.

Output

{ "The Lion King": ["🦁", "πŸ‘‘", "πŸ’", "πŸŒ…", "πŸ¦›"], "The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"], "The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"], "The Matrix": ["πŸ’Š", "πŸ‘¨β€πŸ’»", "πŸ•ΆοΈ", "πŸ”«", "πŸ€–"], "Casablanca": ["✈️", "🎹", "🍸", "🎰", "❀️"], "Raiders of the Lost Ark": ["🏺", "🐍", "πŸ”", "πŸ—ΊοΈ", "πŸ‘’"], "V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸŽ†", "πŸ‡¬πŸ‡§"], "The Princess Bride": ["βš”οΈ", "πŸ‘Έ", "πŸ’•", "πŸ΄β€β˜ οΈ", "πŸ€"], "Back to the Future": ["πŸš—", "⏰", "⚑", "🎸", "πŸ‘Ÿ"], "Dune": ["🏜️", "πŸͺ±", "🌠", "πŸ‘οΈ", "βš”οΈ"] }

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
{
"The Lion King": ["🦁", "πŸ‘‘", "πŸ’", "πŸŒ…", "πŸ¦›"],
"The Nightmare Before Christmas": ["πŸ’€", "πŸŽƒ", "πŸŽ„", "πŸŒ™", "🎡"],
"The Godfather": ["πŸ•΄οΈ", "πŸ”«", "🍝", "🌹", "🎭"],
"The Matrix": ["πŸ’Š", "πŸ‘¨β€πŸ’»", "πŸ•ΆοΈ", "πŸ”«", "πŸ€–"],
"Casablanca": ["✈️", "🎹", "🍸", "🎰", "❀️"],
"Raiders of the Lost Ark": ["🏺", "🐍", "πŸ”", "πŸ—ΊοΈ", "πŸ‘’"],
"V for Vendetta": ["🎭", "πŸ’£", "πŸ—‘οΈ", "πŸŽ†", "πŸ‡¬πŸ‡§"],
"The Princess Bride": ["βš”οΈ", "πŸ‘Έ", "πŸ’•", "πŸ΄β€β˜ οΈ", "πŸ€"],
"Back to the Future": ["πŸš—", "⏰", "⚑", "🎸", "πŸ‘Ÿ"],
"Dune": ["🏜️", "πŸͺ±", "🌠", "πŸ‘οΈ", "βš”οΈ"]
}

PyFunc

Resulting in output: [['🦁', 'πŸ‘‘', 'πŸ’', 'πŸŒ…', 'πŸ¦›'], ['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'], ['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'], ['πŸ’Š', 'πŸ•ΆοΈ', 'πŸ”«', 'πŸ€–'], ['✈️', '🎹', '🍸', '🎰', '❀️'], ['🏺', '🐍', 'πŸ”', 'πŸ—ΊοΈ', 'πŸ‘’'], ['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸŽ†', 'πŸ‡¬πŸ‡§'], ['βš”οΈ', 'πŸ‘Έ', 'πŸ’•', 'πŸ€'], ['πŸš—', '⏰', '⚑', '🎸', 'πŸ‘Ÿ'], ['🏜️', 'πŸͺ±', '🌠', 'πŸ‘οΈ', 'βš”οΈ']]

LLM Generation

Query

For each of the following ten movies described by 5 emoji, give the movie title that best matches. Give your answer as a JSON list. So If I asked for 

1
You might answer 
1
["Finding Nemo", "Toy Story"]]
. Now give me answers for these movies: 
1
2
3
4
5
6
7
8
9
['πŸ’€', 'πŸŽƒ', 'πŸŽ„', 'πŸŒ™', '🎡'],
['πŸ•΄οΈ', 'πŸ”«', '🍝', '🌹', '🎭'],
['πŸ’Š', 'πŸ•ΆοΈ', 'πŸ”«', 'πŸ€–'],
['✈️', '🎹', '🍸', '🎰', '❀️'],
['🏺', '🐍', 'πŸ”', 'πŸ—ΊοΈ', 'πŸ‘’'],
['🎭', 'πŸ’£', 'πŸ—‘οΈ', 'πŸŽ†', 'πŸ‡¬πŸ‡§'],
['βš”οΈ', 'πŸ‘Έ', 'πŸ’•', 'πŸ€'],
['πŸš—', '⏰', '⚑', '🎸', 'πŸ‘Ÿ'],
['🏜️', 'πŸͺ±', '🌠', 'πŸ‘οΈ', 'βš”οΈ']]
What are the names of the movie titles?

Output

Here's my attempt to match movie titles to the given emoji descriptions in JSON format: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

Extract Json

I extracted the following JSON from that output: 

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
[
  "The Lion King",
  "The Nightmare Before Christmas",
  "The Godfather",
  "The Matrix",
  "Casablanca",
  "Raiders of the Lost Ark",
  "V for Vendetta",
  "The Princess Bride",
  "Back to the Future",
  "Dune"
]

PyFunc

OK Resulting in output: True