Triple

T18401377
Position Surface form Disambiguated ID Type / Status
Subject Potts E450003 entity
Predicate hasVariant P455 FINISHED
Object Pott
Pott is a surname and variant of "Potts" associated with various individuals and families, particularly in English-speaking regions.
 E1322468 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: Pott | Statement: [Potts, hasVariant, Pott]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Pott
Context triple: [Potts, hasVariant, Pott]
  • A. Colmonell
    Colmonell is a small rural village in South Ayrshire, Scotland, situated on the River Stinchar and known for its historic church and scenic surroundings.
  • B. Guitteau
    Guitteau is an alternative spelling of the surname Guiteau, most notably associated with Charles J. Guiteau, the assassin of U.S. President James A. Garfield.
  • C. Niesen
    Niesen is a prominent pyramid-shaped mountain in the Swiss Alps overlooking Lake Thun in the Bernese Oberland.
  • D. LEPRA
    LEPRA is a New South Wales statute that sets out and regulates the powers and responsibilities of police and other law enforcement officers.
  • E. Fournier
    Fournier is a French surname borne by numerous notable figures across fields such as music, sports, politics, and the arts.
  • 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: Pott
Triple: [Potts, hasVariant, Pott]
Generated description
Pott is a surname and variant of "Potts" associated with various individuals and families, particularly in English-speaking regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Pott
Target entity description: Pott is a surname and variant of "Potts" associated with various individuals and families, particularly in English-speaking regions.
  • A. Colmonell
    Colmonell is a small rural village in South Ayrshire, Scotland, situated on the River Stinchar and known for its historic church and scenic surroundings.
  • B. Guitteau
    Guitteau is an alternative spelling of the surname Guiteau, most notably associated with Charles J. Guiteau, the assassin of U.S. President James A. Garfield.
  • C. Niesen
    Niesen is a prominent pyramid-shaped mountain in the Swiss Alps overlooking Lake Thun in the Bernese Oberland.
  • D. LEPRA
    LEPRA is a New South Wales statute that sets out and regulates the powers and responsibilities of police and other law enforcement officers.
  • E. Fournier
    Fournier is a French surname borne by numerous notable figures across fields such as music, sports, politics, and the arts.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e5195185b08190bd3b5471cdc047b0 completed April 19, 2026, 6:05 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e24442588190bbf9aec47467c381 completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e38041e08190953c98c4d79ad1eb completed May 13, 2026, 2:35 a.m.
NED2 Entity disambiguation (via description) batch_6a03e3f0f8b081908172ed48ab890d4f completed May 13, 2026, 2:37 a.m.
Created at: April 10, 2026, 10:46 a.m.