Triple

T3254745
Position Surface form Disambiguated ID Type / Status
Subject Kilwa Kisiwani E68268 entity
Predicate hasPart P35 FINISHED
Object Husuni Ndogo
Husuni Ndogo is a small medieval coastal fortification on Kilwa Kisiwani in Tanzania, associated with the historic Swahili trading civilization.
E342445 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: Husuni Ndogo | Statement: [Kilwa Kisiwani, hasPart, Husuni Ndogo]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Husuni Ndogo
Context triple: [Kilwa Kisiwani, hasPart, Husuni Ndogo]
  • A. Gambiri Kati
    Gambiri Kati is an alternative name for the Tregami language, an Indo-Iranian language spoken in parts of eastern Afghanistan.
  • B. Nyanjoga
    Nyanjoga is a Kenyan surname associated with individuals such as Habiba Akumu Nyanjoga.
  • C. Ngozi Olejeme
    Ngozi Olejeme is a Nigerian politician and businesswoman known for her roles in public service and involvement in national development initiatives.
  • D. Mwaghavul
    Mwaghavul is a Chadic language spoken primarily by the Mwaghavul people in Plateau State, central Nigeria.
  • E. Alego Kogelo
    Alego Kogelo is a rural village in western Kenya best known internationally as the ancestral home of former U.S. President Barack Obama’s family.
  • 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: Husuni Ndogo
Triple: [Kilwa Kisiwani, hasPart, Husuni Ndogo]
Generated description
Husuni Ndogo is a small medieval coastal fortification on Kilwa Kisiwani in Tanzania, associated with the historic Swahili trading civilization.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Husuni Ndogo
Target entity description: Husuni Ndogo is a small medieval coastal fortification on Kilwa Kisiwani in Tanzania, associated with the historic Swahili trading civilization.
  • A. Gambiri Kati
    Gambiri Kati is an alternative name for the Tregami language, an Indo-Iranian language spoken in parts of eastern Afghanistan.
  • B. Nyanjoga
    Nyanjoga is a Kenyan surname associated with individuals such as Habiba Akumu Nyanjoga.
  • C. Ngozi Olejeme
    Ngozi Olejeme is a Nigerian politician and businesswoman known for her roles in public service and involvement in national development initiatives.
  • D. Mwaghavul
    Mwaghavul is a Chadic language spoken primarily by the Mwaghavul people in Plateau State, central Nigeria.
  • E. Alego Kogelo
    Alego Kogelo is a rural village in western Kenya best known internationally as the ancestral home of former U.S. President Barack Obama’s family.
  • 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_69ad858f74408190bcbd07f967cd7bd0 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaf65c9388190a0d74d6365ce631e completed March 8, 2026, 5:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28ec9553881908ee96b8684934914 completed March 12, 2026, 10 a.m.
NEDg Description generation batch_69b28f9e12488190b93355b783300264 completed March 12, 2026, 10:04 a.m.
NED2 Entity disambiguation (via description) batch_69b2c092063481909982dea3f71c00c1 completed March 12, 2026, 1:33 p.m.
Created at: March 8, 2026, 3:09 p.m.