May 26, 2026 · 6 min read · Data

Corrected 14 November 2026: the API calls below are ones that work today. The earlier version showed a state_code filter on /v1/cities that does not exist, and made-up answers.

Hyderabad is two cities. Your travel AI should know which one.

Hyderabad, Telangana, India: 10 million people, the Charminar, biryani, Golconda Fort. Hyderabad, Sindh, Pakistan: 1.7 million people, the Pacco Qillo, Mughal-era tombs, distinct cuisine. Generic LLMs without grounding pick one based on surrounding tokens. They are often wrong.

What goes wrong

"Tell me about the Charminar in Hyderabad." Asked plainly, most frontier models answer correctly — Telangana. But change the surrounding context. Mention biryani: still correct. Mention "Sindh region cuisine": the model wavers. Mention "Indus river": a model without grounding can place the Charminar on the Indus. The Charminar is on the Musi.

The model is doing pattern completion across two adjacent high-frequency clusters. Both cities are real. Both have Mughal architecture. Both have distinctive culinary traditions. The statistical signature is similar enough that token bias decides the answer.

The disambiguation key

The fix is structural: never let the system reason about "Hyderabad" without an attached country code, and ideally an attached subdivision code. The find_city tool takes the name and the country code and returns the city's id and its subdivision code; the city context route gives the subdivision's name as well:

POST https://api.travelminds.ai/v1/agent/tool/find_city
Authorization: Bearer YOUR_KEY
Content-Type: application/json

{"name": "Hyderabad", "iso_alpha2": "IN"}

{
  "id": "c3e750a5-9565-4c1d-95f4-b15078044e91",
  "name": "Hyderabad",
  "iso_alpha2": "IN",
  "state_code": "IN-TG",
  "matched_via": "exact_name",
  "alternatives": []
}

GET https://api.travelminds.ai/v1/cities/c3e750a5-9565-4c1d-95f4-b15078044e91/context
Authorization: Bearer YOUR_KEY

{
  "city_id": "c3e750a5-9565-4c1d-95f4-b15078044e91",
  "name": "Hyderabad",
  "iso_alpha2": "IN",
  "admin": {"state_code": "IN-TG", "state_name": "Telangana", ...},
  ...
}

POST https://api.travelminds.ai/v1/agent/tool/find_city

{"name": "Hyderabad", "iso_alpha2": "PK"}

{
  "id": "a0e0859d-3676-4249-9032-104a844b27d5",
  "name": "Hyderabad",
  "iso_alpha2": "PK",
  "state_code": null,
  "matched_via": "exact_name",
  "alternatives": []
}

The country code alone separates these two cities. Inside one country, the subdivision code separates more pairs. Our record for Hyderabad in Pakistan has no subdivision code yet, so its state_code is null in both answers; check for that before you rely on the field. GET /v1/cities has no name filter: it lists cities by score, filtered by iso_alpha2. The country code is also the right primitive for downstream systems — visa rules key off iso_alpha2, transit schedules key off iso_alpha2 plus state, currency keys off iso_alpha2.

Other classic same-name pairs

The product implication

If your AI travel product accepts free-text city names from users and passes them straight to a model, you have a disambiguation bug that surfaces randomly. The fix is to resolve every city name to a (name, iso_alpha2, state_code) triple before the model sees it, and to surface a disambiguation prompt to the user when the triple is ambiguous.

"Did you mean Hyderabad, India or Hyderabad, Pakistan?" is a one-line UI fix that prevents an entire class of confidently wrong answers downstream. The data layer just needs to make that question askable.

Sign up — free See India coverage →