πŸ’» Tilores Studio is now available. Run entity resolution locally on your machine.Download free

Data about the La Guaira, Venezuela earthquake Β· 24 June 2026
We collect data from different sources; we are not the origin of it.

We are a technology company. The records shown here come from several public and partner registries (venezuelareporta.org, Desaparecidos Terremoto Venezuela, and buscatupaciente.com); we don't create them and they are not an official source, and they may be incomplete or inaccurate. Use them only as a lead and always verify with the official registries before acting:

Three registries,
one record per person

After the La Guaira earthquake, several independent efforts collect reports of missing people and lists of hospital patients. The same person is often reported many times β€” sometimes in more than one registry. Tilores combines these sources and deduplicates them into one record per real person β€” without losing any data β€” and leaves every decision in human hands.

We combined three independent registries β€” venezuelareporta.org, Desaparecidos Terremoto Venezuela, and buscatupaciente.com β€” with Tilores entity resolution. We publish the results free to organisations and families searching in Venezuela.


Results

Three registries, combined and deduplicated

Latest entity-resolution run Β· 9 July 2026, 05:04 VET (11:04 CEST)

140,831
Records collected

From three independent sources

107,075
Distinct people

After entity resolution (preliminary)

33,756
Duplicate records merged

β‰ˆ24% of all records were duplicates

Sources: venezuelareporta.org (59,176 records), Desaparecidos Terremoto Venezuela (70,215), and buscatupaciente.com (11,440, hospital patient lists).

The distinct-people total is a preliminary estimate: with more aggressive matching rules, we haven't yet re-verified the over-merge rate.


Status of people

Still missing, located, and yet to match

59,745
Still missing

Only have "missing" reports

23,011
Located

Found, safe, or matched to a hospital patient

24,319
Hospital patients not yet matched

A searchable pool for families still looking

"Still missing" counts open cases in the combined registry (people with only missing reports) β€” not confirmed casualties.


Cross-source overlap

The same person in more than one registry

venezuelareporta.org and Desaparecidos Terremoto Venezuela are independent registries of the same people missing after the earthquake, so they overlap enormously. Entity resolution cross-links them into one record per person.

23,333
In more than one source

The same person recorded in more than one place

23,099
In two registries

Appear in two of the sources

234
In all three registries

Appear in all three sources at once


Hospital screening

Connecting missing-person reports with hospital patients

Hospital patient lists β€” buscatupaciente.com β†— plus Desaparecidos Terremoto Venezuela's hospital lists β€” are screened against the missing-persons registry by national ID (cΓ©dula) and name, to locate people who are alive and in care.

1,134
Linked to a hospital patient

People connected to a hospital patient record (1,853 records linked)

88
Highest-value live leads

Only have a "missing" report and appear as hospital patients

4,928
Reported missing but appear located

A "missing" report plus a "found / safe / hospital" record

Read this carefully. The 88 leads are candidates for human review, not confirmed reunifications. And 24,319 hospital patients remain unmatched: a searchable pool for families still looking.


The challenge

In a crisis, duplicate reports cost time

When many people report at once β€” and across several different registries β€” duplicates are not a cosmetic problem. They inflate the apparent number of missing people, scatter one person's information across many reports, and bury the fact that matters most: that someone has already been found.

Someone comparing several lists by hand cannot reliably tell that "MarΓ­a C. GonzΓ‘lez" and "Maria Gonzalez" are the same person, or that a missing report already has a hospital patient waiting elsewhere in the data.


What Tilores did

Entity resolution, in plain language

Entity resolution is the technology that recognises when several records refer to the same real person, even when the details are written differently. We combined the three sources β€” 140,831 records β€” and resolved them into distinct people. Matching is anchored on the national ID (cΓ©dula), plus name (with phonetic matching), age (within a Β±4-year window), and approximate location.

Safeguards against false matches

On a subject this sensitive, a false positive is worse than no match. So the configuration is deliberately cautious:

Never incompatible data
Records with a conflicting national ID or gender β€” or incompatible ages (>4-year gap) β€” are never merged.
Masked-cΓ©dula guard
No merging across partial or masked national IDs between sources.
Fast and repeatable

We combined 140,831 records from three sources. Entity resolution runs on the instance and refreshes incrementally: each update re-processes only new or changed reports.


Technical detail

The matching rules

Before anything is compared, every field is normalised: accents and capitals are removed, spacing is standardised, and connector words ("de", "la", "los"…) are stripped. Names also go through a Spanish phonetic normalisation β€” b/v, g/j, c/s/z, ll/y, silent h, qu/k β€” so spelling variants line up. The national ID is reduced to digits, and masked IDs (with β€’ or *) are discarded.

Phonetic examples
Vera β‰ˆ Bera
GimΓ©nez β‰ˆ Jimenez
Zavala β‰ˆ Savala
Yolanda β‰ˆ Llolanda

Two reports are merged into the same person when they satisfy one of these rules:

Same national ID (cΓ©dula)

Same cΓ©dula (digits only) and the first name agrees β€” the name check stops a typo in the ID from merging different people.

"V-12,345,678 Β· JosΓ© GonzΓ‘lez" + "12345678 Β· Jose Gonzalez" β†’ same person

Same reporter phone or email

The reporter's phone or email matches + first and last name agree + age equal or empty; compound records are excluded.

Two reports from +58 412-555-1234: "MarΓ­a GonzΓ‘lez, 30" and "Maria Gonzalez" (no age) β†’ same person (re-submission)

Name + age + location

Name (phonetic) + age + a shared distinctive location. Links the same person reported by different people, even across different registries.

"JesΓΊs GimΓ©nez, 24, Playa Grande, NaiguatΓ‘" (venezuelareporta) + "Jesus Jimenez, 25, NaiguatΓ‘" (Desaparecidos Terremoto Venezuela) β†’ same person

And what is never merged
Siblings
The first given name must match and the age can't contradict: "Ana PΓ©rez, 12" and "Luis PΓ©rez, 15" are not merged.
Compound records
Names with "y" or commas ("MarΓ­a y JosΓ©") are flagged as multiple and left out of automatic merging.
Conflicting data
Records with a different national ID or gender β€” or incompatible ages (more than 4 years apart) β€” are never merged.
Masked national ID
Partial IDs (with β€’ or *) are ignored, so an incomplete match can't merge two people.

How the data is used responsibly

Humans stay in control

Every match is a suggestion for human review. A person confirms before any case is closed, because a wrong match could stop the search for someone still missing.

These figures are from the latest resolution run on the current data. The numbers reflect the de-duplicated registry; the raw per-source totals are larger because the same people appear repeatedly.

We'd like to work directly with the teams behind each registry to help better. If you're part of any of these projects β€” or can connect us β€” write to us at hello@tilores.io.


What we delivered

Three deliverables, ready to use

A golden record per person

One record per real person, merging reports from all three sources, with a "found / safe" status if any of their reports indicated one.

Duplicate clusters

33,756 duplicate records merged: which reports are the same person, keeping one primary, using each source’s original identifiers.

Hospital cross-match

Hospital patients linked to their missing-person report by national ID and name, to help locate people who are alive and in care.


What's next Β· How Tilores can help

Prevent duplicates at the source and screen hospital lists

Real-time deduplication via API

Dedupe and search the moment each new report is captured, preventing duplicates at the source instead of cleaning them up afterwards.

Continuous hospital-list screening

Compare lists of admitted or identified patients against the registry to surface likely matches and help reunite people with their families faster.


Would this help? Let's talk.

If you run a registry, a relief effort, or a hospital's data, we'd be glad to talk. Tilores offers this free to those searching in Venezuela.