Triple

T12522302
Position Surface form Disambiguated ID Type / Status
Subject Wheatbelt region E299347 entity
Predicate hasTown P847 FINISHED
Object Kulin
Kulin is a small rural town in Western Australia known for its grain farming, community events, and proximity to the state’s Wheatbelt agricultural areas.
E986584 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: Kulin | Statement: [Wheatbelt region, hasTown, Kulin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kulin
Context triple: [Wheatbelt region, hasTown, Kulin]
  • A. Kulin Nation
    The Kulin Nation is an alliance of several Aboriginal Australian peoples whose traditional lands encompass much of what is now central Victoria, including the area around present-day Melbourne.
  • B. Kantolo
    Kantolo is a rural village in South Africa’s Eastern Cape province, best known as the birthplace of anti-apartheid leader Oliver Tambo.
  • C. Curicica
    Curicica is a residential neighborhood located in the West Zone of Rio de Janeiro, Brazil.
  • D. Mungindi
    Mungindi is a remote Australian town uniquely situated on both sides of the New South Wales–Queensland border, serving as a rural service centre for the surrounding agricultural region.
  • E. Kulon
    Kulon is an extinct Papuan language once spoken in the interior of West Papua, Indonesia.
  • 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: Kulin
Triple: [Wheatbelt region, hasTown, Kulin]
Generated description
Kulin is a small rural town in Western Australia known for its grain farming, community events, and proximity to the state’s Wheatbelt agricultural areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kulin
Target entity description: Kulin is a small rural town in Western Australia known for its grain farming, community events, and proximity to the state’s Wheatbelt agricultural areas.
  • A. Kulin Nation
    The Kulin Nation is an alliance of several Aboriginal Australian peoples whose traditional lands encompass much of what is now central Victoria, including the area around present-day Melbourne.
  • B. Kantolo
    Kantolo is a rural village in South Africa’s Eastern Cape province, best known as the birthplace of anti-apartheid leader Oliver Tambo.
  • C. Kuku
    Kuku are an ethnic group native to South Sudan, primarily inhabiting parts of Central Equatoria and speaking a Bari-related language.
  • D. Curicica
    Curicica is a residential neighborhood located in the West Zone of Rio de Janeiro, Brazil.
  • E. Mungindi
    Mungindi is a remote Australian town uniquely situated on both sides of the New South Wales–Queensland border, serving as a rural service centre for the surrounding agricultural region.
  • 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_69d6ada5cdd48190860d9ce30aff69be completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d9545c2aa081908e8a5a94d30e23eb completed April 10, 2026, 7:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69f64bc159c88190835fea5c0d9ee799 completed May 2, 2026, 7:08 p.m.
NEDg Description generation batch_69f64def9a6081908c3048f948829051 completed May 2, 2026, 7:18 p.m.
NED2 Entity disambiguation (via description) batch_69f64ea1719c8190b91ffaab60db25ad completed May 2, 2026, 7:21 p.m.
Created at: April 8, 2026, 9:57 p.m.