From e4a12c5ff0f19c569bc41c561fd3a3920afd5934 Mon Sep 17 00:00:00 2001 From: lila Date: Fri, 24 Jul 2026 13:45:32 +0200 Subject: [PATCH] updating prompt --- data-pipeline/prompt | 50 ++++++++++++++++++++++++++++---------------- 1 file changed, 32 insertions(+), 18 deletions(-) diff --git a/data-pipeline/prompt b/data-pipeline/prompt index 50fa6d9..09275b0 100644 --- a/data-pipeline/prompt +++ b/data-pipeline/prompt @@ -1,24 +1,30 @@ You are a multilingual lexicographer generating vocabulary data for a language-learning app. -Source language: german +Source language: spanish Part of speech: noun -Target languages: en, it, es, fr +Target languages: en, it, de, fr Input words: -Wand -Dach -Tor -Zaun -Ecke -Mitte -Kante -Oberfläche -Innenstadt -Außenbereich -Umwelt -Gelegenheit -Vorteil -Entscheidung +suelo +pared +techo +portón +valla +esquina +centro +borde +superficie +centro +suburbio +medioambiente +oportunidad +ventaja +decisión +paciencia +comportamiento +industria +conocimiento +solución Return ONLY valid JSON. @@ -33,7 +39,7 @@ Each word object must have this shape: { "headword": string, - "language": "en", + "language": "es", "pos": "noun", "senses": [ { @@ -43,7 +49,7 @@ Each word object must have this shape: "examples": string[], "translations": [ { - "target_language": "de" | "it" | "es" | "fr", + "target_language": "de" | "it" | "en" | "fr", "word": string, "gender": "masculine" | "feminine" | "neuter" | null, "difficulty": "easy" | "medium" | "hard" @@ -184,3 +190,11 @@ Example output shape for the English noun "bank": ] } ] + +For target_language "en", gender MUST ALWAYS be null. English nouns do not have grammatical gender. +CRITICAL: Definitions and examples MUST be written in the SOURCE language specified above. +If source language is German, definitions MUST be in German. +If source language is Spanish, definitions MUST be in Spanish. +If source language is English, definitions MUST be in English. +A translation difficulty must never be lower than its sense difficulty. +Set senses.difficulty to the easiest translation difficulty in that sense.