Methodology

Language models are used as extraction tools in building these records, never as the authority for a fact. A model may locate a passage in a source and pull a value out of it; it does not get to supply the value. If no source states a figure, the field stays empty. An empty field is information — it says the evidence does not exist — and filling it with a plausible guess destroys that.

Evidence is attached per field, not per page. A single wreck may carry separate evidence for its depth, its loss date, its protection status and its position, each with its own source and its own confidence rating. This is why the sources section on a wreck page lists which field each source supports.

Each evidence record has fields for:

• source name, and a source URL where one exists
• source date — when the source itself was published, not when it was read
• the supporting excerpt, so the claim can be checked without leaving the page
• a confidence rating

Those fields are not populated to the same depth. Source name, source URL, excerpt and confidence are present on every evidence record; source dates are not, and most evidence records are undated. A missing date is left missing: inferring one from when the source was read, or from the page it sits on, would manufacture exactly the freshness signal this section claims to provide. The current figures are published on the coverage page.

Verified

Supported by an authoritative source — an official heritage register, a marine survey dataset, or agreement between independent published accounts.

Probable

Supported by a credible single source, typically a specialist website, club record or established wreck register, with nothing contradicting it.

Unknown

Recorded but not corroborated, or drawn from a source whose basis cannot be established. Treated as a lead, not a fact.

A rating describes the strength of the evidence, not the importance of the fact. A verified rating on a depth figure means the sources agree, not that the seabed has been measured to the centimetre.

Sources conflict most often on maximum depth and on position, and less often on casualty figures and loss dates. Where a conflict exists it is stored as a conflict: both values, both sources, and a note on the discrepancy. The wreck page displays it rather than hiding it.

This is deliberate. A record that silently picks one of two depths looks more authoritative and is less useful — the divergence is often the most useful thing a reader can know.

Where sources disagree on the casualties, depth, tonnage, loss date or position, the wreck page shows the record’s figure with the range in sources and a link to the section below. The first recorded conflict is on the Koln, where the same authoritative designation prints a latitude/longitude and a national grid reference that disagree by roughly a kilometre; the grid reference is used for the stored position and the disagreement is kept on the page rather than quietly dropped. How many conflicts are currently recorded is reported on the coverage page, which reads the number from the records rather than restating it here.

Most disagreements between sources have ordinary causes, and naming them helps in reading a record.

• Casualty counts. Some sources count crew and passengers together, others only one; some include people who died of their injuries later; manifests and muster rolls themselves differ.
• Depth. A figure may be measured to chart datum or to the seabed, inferred from a bathymetric survey rather than measured on the wreck, or given for the highest part of the structure rather than the scour beside the hull.
• Position. Coordinates can be given in different datums (OSGB36 against WGS84 differs by over 100 metres in parts of Britain), can come from a register or from a later survey, and can be where a ship was reported lost rather than where her wreck was located.
• Dates. Sources may give the date of an attack, of the sinking, or of a later loss of a raised or salvaged hull, and year-only dates are often expanded inconsistently.

Not every position should be published. A record’s visibility state determines what is shown:

Public exact

Shown to 4 decimal places (about 10 m); only for positions published by an open official source on sites with no legal protection or war-grave status.

Public approximate

Rounded to 2 decimal places (about 1 km); applied to every designated protected wreck and war grave, and to records whose position is only approximately known.

Register only

A precise position exists in an official register; it is not republished here.

Restricted

Position withheld because the site is protected, licensed, or otherwise vulnerable to interference.

Hidden

No position shown. Applied where publication would present a clear risk; war graves are never shown more precisely than about 1 km, and some are withheld entirely.

Where a record has no visibility state set, the position is withheld. The site shows coordinates only for records explicitly marked public exact or public approximate, so an unset or unrecognised state fails closed rather than defaulting to publication.

Position sources: a position is published to about 10 m only when its source permits redistribution; where it does not, it is rounded to about 1 km. The sources and their licences are listed on the attribution page.

Records are revised when a new source is found, when a source is superseded, or when a correction is received. Where an evidence record carries a source date, that date is shown on the entry, so the age of the underlying claim is visible rather than implied by the age of the page. Where it does not, no date is shown and the age of that claim is genuinely unknown.

Wreck sites are not static. Several records on the map describe structures that have collapsed further, been salvaged, or had their legal protection changed since the sources were written. Where a source is old and dated, its date says so; where it is undated, the record cannot tell you how old the claim is, and this page would rather say that than imply currency it cannot support.

No original survey and no guarantee of currency. The map compiles what has been published and shows you where it came from. For the present legal status of a protected site, the relevant authority is the source — not this site.

The same standard applies to the project’s own retrieval benchmark, where measurement limitations are published alongside the results.