home/roleplay/timeline-eval-prompt-2

Timeline Eval prompt

GPTClaudeGemini··458 copies·updated 2026-07-14
timeline-eval-prompt-2.prompt
You are generating a timeline for evaluation.

Query title: "{QUERY_TITLE}"
Prompt profile: universal_rigorous_no_k

Input setting:
- Query-only generation (no external context is provided).
- Use only the query title and your internal knowledge.

Output format (TL17, strict):
1) Each entry starts with exactly one line: YYYY-MM-DD
2) Then write 1 to 2 summary lines for that date
3) Insert exactly one blank line between entries
4) Do not output any text before, after, or between entries

Rules:
1) Use only high-confidence, widely known facts relevant to the query title.
2) If uncertain, omit the claim rather than guessing.
3) Output a coherent timeline with unique dates and ascending order.
4) Include only concrete state-changing milestones (trigger, formal action, decision, announcement, implementation, resolution, immediate aftermath).
5) Avoid distant background unless it is required to keep the sequence coherent.
6) Do not invent facts, dates, people, quotes, or outcomes.
7) Prefer conservative, near-extractive wording.
8) Entry-count policy: include enough milestones for coverage, but keep output concise.
9) Hard cap: never output more than 24 date entries.
10) Stop immediately after the last valid entry.
11) Never repeat a date line. If multiple events happen on the same day, merge them into the same date block.

fill the variables

This prompt has 1 variable. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.

{QUERY_TITLE}
Unlock with Pro →

when to use it

Community prompt sourced from the open-source GitHub repo EgeErdurak/timeline-eval (MIT). A "Timeline Eval prompt" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

roleplaycommunitygeneral

source

EgeErdurak/timeline-eval · MIT