Which date formats are recognized?

ISO dates (2026-06-05), slash and dot formats, written months (June 5, 2026), relative phrases (today, tomorrow, in 3 days, 2 weeks ago), weekday names, and standalone clock times. Each is normalized to ISO 8601 where enough information exists.

How are ambiguous dates handled?

Numeric formats like 03/04/2026 are genuinely ambiguous between month-day and day-month order. The tool flags them and shows both interpretations rather than guessing, so you can pick the correct one based on context.

Why set a reference date?

Relative expressions only have meaning relative to "now." Setting the reference date lets the tool resolve "tomorrow" or "two days ago" to a concrete ISO date instead of leaving it relative. It defaults to today but you can set it to when the LLM output was generated.

Does this run locally?

Yes, entirely in your browser with no network calls. You can paste sensitive content safely. The parsing is heuristic, so always verify flagged or unusual matches before using them programmatically.

What is the Date & Time Extractor from LLM Output?

Paste LLM text to find every date and time expression — absolute, relative, and natural-language — and normalize each to ISO 8601. Relative dates resolve against a reference date you set, and ambiguous formats are flagged with both interpretations. It runs free in your browser on Gera Tools, with nothing uploaded.

Date & Time Extractor from LLM Output

Name: Date & Time Extractor from LLM Output
Creator: Gera Tools
License: https://creativecommons.org/licenses/by/4.0/

Get one useful tool a week

Like this tool? Enter your email and we'll send you one genuinely useful Gera tool a week — plus a link to come back to this one. No spam, one-click unsubscribe any time.

Pull every date out of an LLM answer and normalize it

Language models love to express dates in whatever style the surrounding prose suggests — “next Tuesday,” “06/04/2026,” “in a couple of weeks.” When you need those dates in a database or a calendar, you have to find them and convert them to a single canonical form. This tool scans LLM output, extracts every date and time expression, and normalizes each to ISO 8601.

Why date normalization is needed

LLMs do not output dates in a consistent format. In a single response a model might write “June 5th,” “05/06/2026,” “the fifth of June,” “next Thursday,” and “Q2 2026” — all referring to the same or related dates. Feeding any of those formats directly into a database field or a calendar API requires parsing; feeding mixed formats requires knowing which convention each one uses, which varies by country, context, and training data. ISO 8601 (YYYY-MM-DD) is the one format that is unambiguous, sortable, and accepted by every database and API. This tool converts everything to that standard automatically.

What gets extracted

Expression type	Example	How it resolves
ISO date	2026-06-05	Returns as-is
Slash date (US)	06/04/2026	Flagged — ambiguous; shows MM/DD and DD/MM
Written month	June 5, 2026	2026-06-05
Relative phrase	”in 3 days”	Resolved against your reference date
Relative phrase	”two weeks ago”	Resolved against your reference date
Weekday	”next Thursday”	Resolved to the next Thursday from reference
Clock time	14:30, 2:30 PM	Appended to the resolved date if present

How it works

The parser matches several families of expressions: absolute numeric dates, written-month dates, relative phrases (“today,” “in 3 days,” “two weeks ago”), weekday names, and clock times. Relative phrases are resolved against the reference date you set. Genuinely ambiguous numeric formats — where day and month could be swapped — are not guessed; instead the tool flags them and shows both possible interpretations, so you stay in control.

Tips and caveats

Set the reference date to when the output was produced, not always today, or “tomorrow” will resolve incorrectly for older text.
Trust the flags. A flagged 03/04/2026 means the tool genuinely cannot tell month-first from day-first — decide from context. US text typically uses MM/DD; UK and most European text uses DD/MM.
Verify before automating. Heuristic extraction is excellent for triage but should be checked before feeding results into a scheduling system.
Pair it with the number extractor to fact-check both the figures and the dates an LLM cites in the same answer.
Relative expressions in a model response are relative to when the model produced the response, not when you read it — set the reference date accordingly.