Triple

T3385737
Position Surface form Disambiguated ID Type / Status
Subject Kadavu E71296 entity
Predicate hasSettlement P1068 FINISHED
Object Vunisea
Vunisea is a small coastal village that serves as the administrative and commercial center of Kadavu Island in Fiji.
 E352339 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: Vunisea | Statement: [Kadavu, hasSettlement, Vunisea]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vunisea
Context triple: [Kadavu, hasSettlement, Vunisea]
  • A. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • B. Nembe
    Nembe is an Ijaw subgroup and town in Bayelsa State, Nigeria, known historically as a coastal trading center in the Niger Delta.
  • C. Riaba
    Riaba is a small town on Bioko Island in Equatorial Guinea, known historically as one of the island’s early colonial settlements.
  • D. Wainganga
    Wainganga is a major river in central India that flows through the states of Madhya Pradesh and Maharashtra before joining other rivers on its way to the Godavari basin.
  • E. Eulau
    Eulau is a German-language surname associated with individuals such as political scientist Heinz Eulau.
  • 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: Vunisea
Triple: [Kadavu, hasSettlement, Vunisea]
Generated description
Vunisea is a small coastal village that serves as the administrative and commercial center of Kadavu Island in Fiji.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vunisea
Target entity description: Vunisea is a small coastal village that serves as the administrative and commercial center of Kadavu Island in Fiji.
  • A. Tamba
    Tamba is a city located in Hyogo Prefecture, Japan, known for its rural landscapes, traditional pottery, and historical sites.
  • B. Nembe
    Nembe is an Ijaw subgroup and town in Bayelsa State, Nigeria, known historically as a coastal trading center in the Niger Delta.
  • C. Riaba
    Riaba is a small town on Bioko Island in Equatorial Guinea, known historically as one of the island’s early colonial settlements.
  • D. Wainganga
    Wainganga is a major river in central India that flows through the states of Madhya Pradesh and Maharashtra before joining other rivers on its way to the Godavari basin.
  • E. Eulau
    Eulau is a German-language surname associated with individuals such as political scientist Heinz Eulau.
  • 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_69ad85a8fd9c819095ecedf838d2bf1b completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb662d190819085b211dac85a83b2 completed March 8, 2026, 5:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b33455ae2481908e6478cb240b31c1 completed March 12, 2026, 9:47 p.m.
NEDg Description generation batch_69b334f75e708190aed8b388c9ea55d2 completed March 12, 2026, 9:49 p.m.
NED2 Entity disambiguation (via description) batch_69b3359bbf388190979c6003a9ed05b2 completed March 12, 2026, 9:52 p.m.
Created at: March 8, 2026, 3:14 p.m.