Triple

T16442934
Position Surface form Disambiguated ID Type / Status
Subject Gedo E399348 entity
Predicate hasBorderTown P847 FINISHED
Object El Wak
El Wak is a town located on the Somalia–Kenya border, serving as an important cross-border trading and transit point in the Gedo region.
E1214475 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: El Wak | Statement: [Gedo, hasBorderTown, El Wak]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: El Wak
Context triple: [Gedo, hasBorderTown, El Wak]
  • A. El Wak
    El Wak is a small border town in northeastern Kenya near the Somali frontier, serving as a local trading and transit hub in the arid region.
  • B. Al Ras
    Al Ras is one of Dubai’s oldest commercial districts, known for its traditional markets, historic streets, and proximity to Dubai Creek.
  • C. Al Said
    Al Said is the ruling royal family of Oman, known for its long-standing dynasty that has governed the country since the mid-18th century.
  • D. Al Wahat
    Al Wahat is a region in northeastern Libya known for its desert oases and role in the country’s oil-producing area.
  • E. Al Twar
    Al Twar is a residential and commercial locality in eastern Dubai, United Arab Emirates, known for its community facilities and proximity to major transport links.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: El Wak
Triple: [Gedo, hasBorderTown, El Wak]
Generated description
El Wak is a town located on the Somalia–Kenya border, serving as an important cross-border trading and transit point in the Gedo region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: El Wak
Target entity description: El Wak is a town located on the Somalia–Kenya border, serving as an important cross-border trading and transit point in the Gedo region.
  • A. El Wak
    El Wak is a small border town in northeastern Kenya near the Somali frontier, serving as a local trading and transit hub in the arid region.
  • B. Al Ras
    Al Ras is one of Dubai’s oldest commercial districts, known for its traditional markets, historic streets, and proximity to Dubai Creek.
  • C. Al Said
    Al Said is the ruling royal family of Oman, known for its long-standing dynasty that has governed the country since the mid-18th century.
  • D. Al Wahat
    Al Wahat is a region in northeastern Libya known for its desert oases and role in the country’s oil-producing area.
  • E. Al Twar
    Al Twar is a residential and commercial locality in eastern Dubai, United Arab Emirates, known for its community facilities and proximity to major transport links.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32cd8d2988190acb5722a15623319 completed April 18, 2026, 7:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a004f4b738881908f8a205466397f33 completed May 10, 2026, 9:26 a.m.
NEDg Description generation batch_6a0050751be48190a76ab998b544ac5a completed May 10, 2026, 9:31 a.m.
NED2 Entity disambiguation (via description) batch_6a0050d99f7c81909a5d5582294790f7 completed May 10, 2026, 9:33 a.m.
Created at: April 10, 2026, 5:10 a.m.