Triple

T1868088
Position Surface form Disambiguated ID Type / Status
Subject Norfolk Island E34968 entity
Predicate capital P234 FINISHED
Object Kingston
Kingston is the small historic administrative center and main settlement of Norfolk Island, an external territory of Australia in the Pacific Ocean.
 E207830 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: Kingston | Statement: [Norfolk Island, capital, Kingston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kingston
Context triple: [Norfolk Island, capital, Kingston]
  • A. Kingston
    Kingston is the largest city of Jamaica and its political, cultural, and economic center.
  • B. Kingston
    Kingston is a small city in eastern Tennessee that serves as the county seat of Roane County and lies within the greater Knoxville metropolitan area.
  • C. Kingston
    Kingston is a small unincorporated community and historic mining town located in central Nevada, United States.
  • D. Kingston
    Kingston is a coastal town in Plymouth County, Massachusetts, known for its historic New England character and proximity to Cape Cod Bay.
  • E. Kingston
    Kingston is a historic city in New York State known for being one of the state’s early capitals and a key cultural and economic center in the Hudson Valley region.
  • 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: Kingston
Triple: [Norfolk Island, capital, Kingston]
Generated description
Kingston is the small historic administrative center and main settlement of Norfolk Island, an external territory of Australia in the Pacific Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kingston
Target entity description: Kingston is the small historic administrative center and main settlement of Norfolk Island, an external territory of Australia in the Pacific Ocean.
  • A. Kingston
    Kingston is a historic city in New York State known for being one of the state’s early capitals and a key cultural and economic center in the Hudson Valley region.
  • B. Kingston
    Kingston is a coastal town in Plymouth County, Massachusetts, known for its historic New England character and proximity to Cape Cod Bay.
  • C. Kingston
    Kingston is the largest city of Jamaica and its political, cultural, and economic center.
  • D. Kingston
    Kingston is a small city in eastern Tennessee that serves as the county seat of Roane County and lies within the greater Knoxville metropolitan area.
  • E. Kingston
    Kingston is a historic Canadian city in eastern Ontario, located where the St. Lawrence River meets Lake Ontario, known for its limestone architecture and role as a former capital of the Province of Canada.
  • 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_69a88600b2f88190bc09303e68ab517e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69abb0b6ac108190921c197abc5ab5b5 completed March 7, 2026, 4:59 a.m.
NED1 Entity disambiguation (via context triple) batch_69add1d8dd8881909189029a047bc2b4 completed March 8, 2026, 7:45 p.m.
NEDg Description generation batch_69add28b804c8190a625e5d1405c59be completed March 8, 2026, 7:48 p.m.
NED2 Entity disambiguation (via description) batch_69add35731588190a13c969490ca2c09 completed March 8, 2026, 7:51 p.m.
Created at: March 4, 2026, 7:34 p.m.