Triple

T17524716
Position Surface form Disambiguated ID Type / Status
Subject Bua E426764 entity
Predicate hasSettlement P1068 FINISHED
Object Lekutu
Lekutu is a township in Fiji’s Bua Province on the island of Vanua Levu, serving as a local center for surrounding rural communities.
E1274043 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: Lekutu | Statement: [Bua, hasSettlement, Lekutu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lekutu
Context triple: [Bua, hasSettlement, Lekutu]
  • A. Mabalako
    Mabalako is a health zone in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected by Ebola outbreaks.
  • B. Mokorotlo
    Mokorotlo is a traditional Basotho conical hat, typically woven from grass, that serves as a national cultural symbol of Lesotho.
  • C. Thokoza
    Thokoza is a township in the East Rand region of Gauteng, South Africa, historically known for its role in anti-apartheid struggles and community activism.
  • D. Makgoba
    Makgoba is a South African surname most prominently associated with Thabo Makgoba, the Anglican Archbishop of Cape Town.
  • E. Tlokwa
    Tlokwa is a Sotho–Tswana-speaking ethnic group in Southern Africa, historically organized into chiefdoms and known for its distinct cultural and linguistic identity within the broader Sotho–Tswana peoples.
  • 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: Lekutu
Triple: [Bua, hasSettlement, Lekutu]
Generated description
Lekutu is a township in Fiji’s Bua Province on the island of Vanua Levu, serving as a local center for surrounding rural communities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Lekutu
Target entity description: Lekutu is a township in Fiji’s Bua Province on the island of Vanua Levu, serving as a local center for surrounding rural communities.
  • A. Mabalako
    Mabalako is a health zone in North Kivu Province in the eastern Democratic Republic of the Congo, known for being heavily affected by Ebola outbreaks.
  • B. Mokorotlo
    Mokorotlo is a traditional Basotho conical hat, typically woven from grass, that serves as a national cultural symbol of Lesotho.
  • C. Thokoza
    Thokoza is a township in the East Rand region of Gauteng, South Africa, historically known for its role in anti-apartheid struggles and community activism.
  • D. Makgoba
    Makgoba is a South African surname most prominently associated with Thabo Makgoba, the Anglican Archbishop of Cape Town.
  • E. Tlokwa
    Tlokwa is a Sotho–Tswana-speaking ethnic group in Southern Africa, historically organized into chiefdoms and known for its distinct cultural and linguistic identity within the broader Sotho–Tswana peoples.
  • 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_69d889de677081909b22d2657b1f0292 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e452d592a081909bf876d606158b2d completed April 19, 2026, 3:58 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01c9473100819081079a0db51391cc completed May 11, 2026, 12:19 p.m.
NEDg Description generation batch_6a01cb2016f8819090e8ec20428cfdaf completed May 11, 2026, 12:27 p.m.
NED2 Entity disambiguation (via description) batch_6a01cbad7bf481909c754049686c5b39 completed May 11, 2026, 12:29 p.m.
Created at: April 10, 2026, 5:49 a.m.