Skip to content
InterlineaDocs
ConceptsAnalyses and contextDocs menu

Analyses and context

The stored word-by-word analyses and context notes: what they hold, when they exist, and why the API never makes new ones.

Interlinea's reader explains every word of a text. The API and the MCP server give you those explanations once they are stored. They never call a language model, so they cost nothing and answer the same way every time.

When an analysis exists

  • Every graded passage is analysed in full.
  • A library section is analysed the first time a reader opens it in Interlinea. From then on everyone gets the stored analysis, here and in the reader.
  • A sentence with no stored analysis comes back with translation: null and words: null. analysed and total say how much of a text is covered.

To have a section analysed, open its url in Interlinea.

What a word carries

Each word follows the Universal Dependencies conventions for parts of speech, features and relations:

Word
NameDescription
iinteger1-based index of the word in its sentence.
formstringThe word as printed.
lemmastringDictionary headword; Latin with macrons, Greek polytonic.
entrystring or nullDictionary entry: principal parts, or genitive and gender.
uposstringUniversal Dependencies part of speech.
featsstringUniversal Dependencies features, e.g. "Case=Acc|Gender=Neut|Number=Plur"; "_" if none.
headintegerIndex of the word this one depends on; 0 for the root.
deprelstringUniversal Dependencies relation to its head: nsubj, obj, amod, …
glossstringMeaning in this sentence, 1 to 4 words.
notestring or nullOne sentence on the word's role.
encliticobjectOptionalPresent only when an enclitic rides on the word, e.g. -que "and".
2 fields
enclitic fields
formstring
glossstring

A language model makes the analyses, and rules check them: each word analysed exactly once, one root per sentence, no loops, and grammar labels valid for the language. They can still be wrong, especially in Greek. Treat them as a careful reading, not an answer key.

Context notes

Context notes say where a text sits in its work: what has happened so far, what happens here (never a translation), the people, gods and places named, what comes next, and a few lines on the work.

Context
NameDescription
machineWrittenbooleanFalse for the graded passages' hand-written notes.
sectionobject or nullNull until someone has opened Context for this part in the reader.
4 fields
section fields
soFarstring or nullWhat has happened in the work before this part.
herestring or nullWhat happens in this part, never a translation.
peoplearray of objectPeople, gods and places named here.
4 fields
people fields
namestring
notestring
formsarray of stringThe words in the text that name them.
wikipediastring or nullEnglish Wikipedia article title, when certain.
nextstring or nullWhat comes next.
workobject or nullA few lines about the work.
2 fields
work fields
introstring or null
notestring or null
  • Graded passages have hand-written, checked notes, with machineWritten false.
  • A library section's notes are written by a model the first time a reader opens Context in Interlinea, then stored, with machineWritten true. Until then section is null.

Getting them

  • include=analysis,context on a text endpoint adds both to the text. Over MCP, pass include: ["analysis", "context"] to get_text.
  • /api/v1/analysis and get_analysis return the analysis on its own; sentence picks one sentence, counting from 0.
  • /api/v1/context and get_context return the notes on their own.
  • /api/v1/words and lookup_word find a headword across every stored analysis, with cited sentences.

include is opt-in because analyses are large: a graded passage with its analysis is about 22 KB of JSON, against about 3 KB for its text.