British Museum Acquisitions from Spink and Sons: analysis with ChatGPT prompts

 QUESTION TO CHATGPT (code interpreter)

Spink and Sons is an art dealer involved in selling many looted artifacts. Please examine this file and tell me three ways it could be analysed to rank artworks most likely to have been looted

- Spink prov British Museum.csv

ChatGPT response

The dataset seems to contain information about the artworks dealt by Spink and Sons, with details such as:

• goog_34287676The type of the item (Type)
• Accession number (Accession Number)
• Description of the item (Description)
• The materials used (Materials)
• The techniques used (Techniques)
• Dimensions (Dimension)
• Current location of the item (Location)
• Acquisition date (Acquisition date)
• Provenance (Provenance)
• Curators comments (Curators Comments)
• Bibliographic references (Bibliographic)
• Associated names (Associated Names)
• Previous owner (Previous Owner)
• Excavation information (Excavation)
• Date of the item (Date)
• Exhibition history (Exhibition History)
• Acquisition notes (Acquisition Notes)
• Artist and School details (Artist, School)

Here are three ways the data could be analyzed to rank artworks most likely to have been looted:

1. Provenance Analysis: The 'Provenance' column can provide critical information regarding the item's history of ownership. If the provenance is incomplete, unclear, or points to a period or region known for looting, the item may be more likely to have been looted.

2. Excavation Information: If the 'Excavation' column indicates that the artwork was found in a context or manner that suggests unauthorized or illegal excavation, it might be more likely to have been looted.

3. Date of Acquisition: The 'Acquisition date' can also provide clues. For example, if the acquisition date is during or shortly after a period of conflict or instability in the country of origin, it may suggest that the item was looted.

Let's do a high-level analysis on these three points. I'll check for missing data in 'Provenance', 'Excavation' and 'Acquisition date' columns to begin with.

Finished working

Show work

I apologize for the confusion, it seems there is no 'Provenance' column in the dataset. Instead, we have a 'Previous Owner' column which might serve a similar purpose, as it gives information about the previous possession of an item. Let's check for missing data in 'Previous Owner', 'Excavation', and 'Acquisition date' columns instead.

Finished working

Show work

I apologize for the oversight, it seems there is no 'Acquisition date' column in the dataset. Let's move forward with the analysis using the 'Previous Owner' and 'Excavation' columns. We can also use the 'Acquisition Notes' column which might contain relevant information about how the item was acquired. Let's check for missing data in 'Previous Owner', 'Excavation', and 'Acquisition Notes' columns.

Finished working

Show work

Based on the initial analysis, we have:

• 443 missing entries in the 'Previous Owner' column
• 478 missing entries in the 'Excavation' column
• 441 missing entries in the 'Acquisition Notes' column

Here's how we could proceed:

Previous Owner Analysis: Artworks with missing 'Previous Owner' information could be considered more suspicious as it could imply that the ownership history is unclear or incomplete.

Excavation Analysis: Artworks with missing 'Excavation' information could also be a cause for concern. If the artwork was found in a context or manner that suggests unauthorized or illegal excavation, it might be more likely to have been looted.

Acquisition Notes Analysis: Similar to the 'Previous Owner' and 'Excavation' columns, artworks with missing 'Acquisition Notes' may suggest that the details about how the item was acquired are unclear, possibly indicating that the item might have been looted.

It's important to note that while these methods can provide indicators, they aren't definitive proof of looting. Further detailed analysis and investigation would be needed to make a more concrete determination.

QUESTION TO CHATGPT (code interpreter)

please create a datavisualization to help readers understand the content

ChatGPT response

Here is a bar chart representing the number of missing entries in the 'Previous Owner', 'Excavation', and 'Acquisition Notes' columns. As you can see, these key columns have a significant amount of missing data, which may indicate items with a higher likelihood of being looted.

Please note that this is a high-level visualization and actual determination of whether an artwork is looted or not would require a more in-depth investigation.

QUESTIONS TO CHATGPT (code interpreter) to create a dataviz by department and by year (a dialog in several parts)

Let's look at the Accession Number. The first four digits represent the YEAR. Please analyze the years of acquisitions of the items by department.

please focus on 1900 to 2021, and represent the departments in a stacked bar

please change the color scheme so that the reader can distinguish the departments more easily

ChatGPT response (for Spink British Museum dataset)