Chimera
A graph of actors with profiles and the links between them, tied to the news. Its own graph engine.
Chimera keeps the actors: states, people, organisations, companies, groups, places, events, assets. Each one has a type, aliases, and relations to other actors, weighted by how often they appear together in the news. Where there is enough material, a local language model writes a profile: motivations, traits, leverage points.
The graph runs on an embedded engine chosen for the purpose and switched over on 31 May 2026. Actors arrive from Retina: every entity the news pipeline extracts becomes a candidate, and a spike around a name triggers a fresh profile. Ownership and sanctions registers sit alongside, several hundred thousand edges, but they barely touch the news actors: measured in July, 53 links could be drawn both ways. That join is parked, not built.
What is not yet there, stated plainly. A profile cannot be traced back to the articles it was drawn from; the pipeline does not keep that link, and a checking tool cannot either. About one actor in thirteen carries another actor’s name as an alias, the residue of an automatic merge that is still being cleaned up; a layer of confirmed same-actor links, 84 so far, is the fix in progress. Six large state actors have been curated by hand and are locked against automatic overwriting. The numbers below are read from the running system on the day of the snapshot; the graph grows while you read.
What goes in
Snapshot 3 September 2026Actors arrive from Retina: every entity the news pipeline extracts becomes a candidate. What the graph adds is structure: a type, aliases, relations to other actors weighted by how often they appear together, and, for 8,157 of the 12,307, a profile written by a local model.
Actors by type
- not yet typed3,010
- people2,939
- cities1,243
- companies1,127
- organisations1,037
- regions651
- events534
- institutions441
- assets399
- countries373
- concepts186
- platforms93
- groups93
- parties82
"Not yet typed" is honest: 3,010 actors are in the graph but have not been classified.
Relations
- relates826,643
- expressed5,006
- about5,006
- mentions2,217
Bars on a log scale. "Relates" is co-mention in the news; "expressed" and "about" carry stances; "mentions" links to articles.
What comes out
Most connected actors
| actor | type | relations |
|---|---|---|
| United States | country | 3,481 |
| Russia | country | 2,481 |
| China | country | 2,430 |
| Iran | country | 1,997 |
| Israel | country | 1,297 |
| Hezbollah | group | 1,116 |
| TASS | media | 1,034 |
| Venezuela | country | 985 |
| Israel | country | 914 |
| Thailand | country | 889 |
| Bloomberg | media | 840 |
| TikTok | platform | 761 |
| Telegram | platform | 698 |
| Palestinians | group | 602 |
| Israel | country | 597 |
| Hamas | group | 597 |
One actor and its neighbourhood: United States
The strongest relations of a single actor, weight from co-mention in the news.
- Islamic State0.87
- Iran0.30
- Mossad0.26
- Rosatomexport Corporation (Rostec)0.24
- Newark0.24
- MBDA0.20
- Gripen0.19
- US Cellular0.19
- Elbit Systems0.19
- Тунгуска-М10.18
- Группа войск «Центр»0.17
- Pakistan Tehreek-e-Insaf0.15
- US CENTCOM0.14
- Iranian Parliament0.14
- F-35 Lightning II0.13
- Hormuz Strait0.13
- Patriot0.12
- Україна0.12
One type at a time
The bar chart above is a headcount. This is what each type actually contains: the best connected actors of that type, with the number of relations behind each name, and for the leading one the relations themselves.
people
2,939 in the graph- Javier Rubio406
- Mark Rutte268
- Rima Hassan42
- Carsten Breuer0
- Florian Seibel0
Strongest relations of Javier Rubio
- JP Morgan · companies0.8238
- Daniel Jalkut · people0.7889
- Dario Amodei · people0.3031
- Sundar Pichai · people0.2954
- FIFA World Cup · events0.2015
- DeepMind · organisations0.1388
cities
1,243 in the graph- Hamburg238
- Bagicz153
- Lampedusa136
- Renk116
- Palo Alto114
Strongest relations of Hamburg
- Magdeburger Weihnachtsmarkt · events0.1303
- Siegburg · cities0.1218
- Polen · not yet typed0.121
- Poland · countries0.1168
- Ansaru · organisations0.0954
- Immigration and Customs Enforcement · organisations0.0906
companies
1,127 in the graph- Shell254
- Cisco Systems125
- Bain Capital105
- Quantum Systems GmbH94
- Helsing GmbH83
Strongest relations of Shell
- AstraZeneca · companies0.48
- Ocado Group · companies0.3444
- Manchester City · cities0.3333
- JP Morgan · companies0.2845
- Lloyds · companies0.2656
- Nationwide · companies0.2488
organisations
1,037 in the graph- International Rescue Committee132
- International Council on Ethics111
- All Girls Foundation for Development29
- Pharmaceuticals Action Committee0
- Humanitarian Needs Response Platform0
Strongest relations of International Rescue Committee
- UN Women · not yet typed0.2417
- OCHA · organisations0.1689
- UNFPA · institutions0.1633
- Protection Cluster · organisations0.1402
- Administración Pública Nacional · not yet typed0.0985
- All Girls Foundation · not yet typed0.0815
regions
651 in the graph- Central Africa236
- Krasnodar Krai201
- Poltava Oblast130
- Komodo National Park106
- Maputo Province95
Strongest relations of Central Africa
- Cornwall · regions0.1521
- EFAS · companies0.1179
- International Paper Company · organisations0.105
- El Niño · events0.0968
- Côte d'Ivoire · countries0.0886
- Madagascar · countries0.0877
events
534 in the graph- China Development Forum100
- Karachi Fire0
- US-Israeli-Iran Conflict0
- Iran War0
- Ukraine EU Accession0
Strongest relations of China Development Forum
- République centrafricaine · countries0.2121
- UNHCR · institutions0.1699
- IFRC · not yet typed0.16
- Fédération Internationale de Football Association · organisations0.1587
- WFP · institutions0.1533
- Health Cluster · organisations0.1517
institutions
441 in the graph- Senate Banking Committee196
- UK Parliament169
- Federal Office for the Protection of the Constitution136
- Executive Branch of the United States Government126
- Cybersecurity and Infrastructure Security Agency28
Strongest relations of Senate Banking Committee
- Genius · organisations0.2091
- Securities and Exchange Commission · organisations0.2084
- CLARITY Act · concepts0.1984
- Commodity Futures Trading Commission · organisations0.1321
- Coinbase · companies0.1053
- Congress · institutions0.0974
assets
399 in the graph- Shahed41
- Dow Jones13
- Iskander Muhammad0
- Trove Token0
- Pendle Token0
Strongest relations of Shahed
- Donetsk · cities0.0227
- Russian forces · not yet typed0.0223
- Odesa Oblast · regions0.0138
- Odesa region · not yet typed0.0135
- Kharkiv Oblast · regions0.0114
- Запорожский фронт · regions0.0059
countries
373 in the graph- United States3,481
- Russia2,481
- China2,430
- Iran1,997
- Israel1,297
concepts
186 in the graph- International Monetary System117
- World Order24
- Transatlantic0
- Humanitarian Situation Monitoring0
- Pig Butchering0
platforms
93 in the graph- TikTok761
- Telegram698
- ChatGPT591
- WhatsApp587
- Claude Code367
groups
93 in the graph- Hezbollah1,116
- Palestinians602
- Hamas597
- Boko Haram314
- SDF262
parties
82 in the graph- CDU418
- Green Party399
- FDP298
- CSU251
- Barisan Nasional232
media outlets
76 in the graph- TASS1,034
- Bloomberg840
- Agence France-Presse448
- Axios295
- Forbes279
movements
15 in the graph- Make America Great Again300
- Peronism263
- Kirchnerismo181
- Sikhism169
- Formula One168
Two things this does not claim. The relation type is almost always RELATES, which means "appeared together in the same reporting", not a stated link between the two. And the quality varies by type: for an aid organisation the relations read like a sector map, for others they are looser. Shown as measured, not curated. Examples are drawn from actors that carry a profile, so a type with many entries can still show few.