Triple

T19799913
Position Surface form Disambiguated ID Type / Status
Subject Diyaluma Falls E475644 entity
Predicate near P350 FINISHED
Object Koslanda
Koslanda is a small town in Sri Lanka’s Badulla District, known as a gateway to the scenic hill country and nearby waterfalls such as Diyaluma Falls.
 E1395480 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: Koslanda | Statement: [Diyaluma Falls, near, Koslanda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Koslanda
Context triple: [Diyaluma Falls, near, Koslanda]
  • A. Mulk
    Mulk is the name of one of the nineteen months in the Badíʻ (Baháʼí) calendar, associated with the concept of dominion or sovereignty.
  • B. Kosuta
    Košuta is a prominent mountain ridge in the Karawanks range on the border between Slovenia and Austria, known for its long, scenic crest and popular hiking routes.
  • C. Ladania
    Ladania is a town located in the Madhubani district of the Indian state of Bihar.
  • D. Korissia
    Korissia is a coastal village and main port of the Greek island of Kea in the Cyclades.
  • E. Krain
    Krain is the historical German name for the Duchy of Carniola, a former Habsburg crown land located in what is now largely central Slovenia.
  • 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: Koslanda
Triple: [Diyaluma Falls, near, Koslanda]
Generated description
Koslanda is a small town in Sri Lanka’s Badulla District, known as a gateway to the scenic hill country and nearby waterfalls such as Diyaluma Falls.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Koslanda
Target entity description: Koslanda is a small town in Sri Lanka’s Badulla District, known as a gateway to the scenic hill country and nearby waterfalls such as Diyaluma Falls.
  • A. Mulk
    Mulk is the name of one of the nineteen months in the Badíʻ (Baháʼí) calendar, associated with the concept of dominion or sovereignty.
  • B. Kosuta
    Košuta is a prominent mountain ridge in the Karawanks range on the border between Slovenia and Austria, known for its long, scenic crest and popular hiking routes.
  • C. Ladania
    Ladania is a town located in the Madhubani district of the Indian state of Bihar.
  • D. Korissia
    Korissia is a coastal village and main port of the Greek island of Kea in the Cyclades.
  • E. Krain
    Krain is the historical German name for the Duchy of Carniola, a former Habsburg crown land located in what is now largely central Slovenia.
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e653cb865c81909696d2b37476f62f completed April 20, 2026, 4:26 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07c50696588190a54cc249f2218b26 completed May 16, 2026, 1:14 a.m.
NEDg Description generation batch_6a07c6509f4c8190aee658954c6cf920 completed May 16, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_6a07c7549de08190916e3e48125beebb completed May 16, 2026, 1:24 a.m.
Created at: April 10, 2026, 1:49 p.m.