Triple

T6041347
Position Surface form Disambiguated ID Type / Status
Subject Lake Wakatipu E134551 entity
Predicate hasTownOnShore P969 FINISHED
Object Kingston
Kingston is a small lakeside town in New Zealand located at the southern end of Lake Wakatipu, known as a gateway to the Queenstown-Lakes district.
E566513 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: [Lake Wakatipu, hasTownOnShore, Kingston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kingston
Context triple: [Lake Wakatipu, hasTownOnShore, Kingston]
  • A. Kingston
    Kingston is a common English surname of Anglo-Saxon origin, historically associated with various towns named Kingston in England.
  • B. 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.
  • C. 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.
  • D. Kingston
    Kingston is a small unincorporated community and historic mining town located in central Nevada, United States.
  • E. Kingston
    Kingston is a borough in northeastern Pennsylvania, United States, situated along the Susquehanna River near the city of Wilkes-Barre.
  • 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: [Lake Wakatipu, hasTownOnShore, Kingston]
Generated description
Kingston is a small lakeside town in New Zealand located at the southern end of Lake Wakatipu, known as a gateway to the Queenstown-Lakes district.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kingston
Target entity description: Kingston is a small lakeside town in New Zealand located at the southern end of Lake Wakatipu, known as a gateway to the Queenstown-Lakes district.
  • A. Kingston chosen
    Kingston is a small settlement in New Zealand’s South Island, located at the southern end of Lake Wakatipu and known as a gateway to the Queenstown-Lakes district.
  • B. Kingston
    Kingston is a small waterfront community in Washington State known as a ferry terminal town on the Kitsap Peninsula.
  • C. Kingston
    Kingston is a residential suburb located on Portsea Island in the city of Portsmouth, England.
  • D. 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.
  • E. 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.
  • F. None of above.

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_69c00875db5c819099dd5bb833ec43c2 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c056d11370819096ac35349bd91f4e completed March 22, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69c1251a3bec81909a654976712f147d completed March 23, 2026, 11:33 a.m.
NEDg Description generation batch_69c1299e4b788190a28069de0ce2d2db completed March 23, 2026, 11:53 a.m.
NED2 Entity disambiguation (via description) batch_69c12a072b348190b576ee132a5d87be completed March 23, 2026, 11:54 a.m.
Created at: March 22, 2026, 4:08 p.m.