Triple

T16636433
Position Surface form Disambiguated ID Type / Status
Subject de Ross E404215 entity
Predicate hasSpellingVariant P457 FINISHED
Object De Ross
De Ross is a surname that may refer to various individuals, often of European origin, and can appear with different capitalization or spacing variants.
E1224439 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: De Ross | Statement: [de Ross, hasSpellingVariant, De Ross]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: De Ross
Context triple: [de Ross, hasSpellingVariant, De Ross]
  • A. Roos
    Roos is a variant of the name Rose, often used as a given name or surname in various European languages.
  • B. Roos
    Roos is the common nickname for the North Melbourne Football Club, an Australian rules football team in the Australian Football League.
  • C. Roos
    The Roos are the athletic teams representing the University of Missouri–Kansas City in NCAA competition.
  • D. Mollerussa
    Mollerussa is a small town in the province of Lleida, Catalonia, Spain, known for its agricultural surroundings and regional commercial services.
  • E. Ballaison
    Ballaison is a small commune in the Haute-Savoie department of southeastern France, near the Swiss border and Lake Geneva.
  • 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: De Ross
Triple: [de Ross, hasSpellingVariant, De Ross]
Generated description
De Ross is a surname that may refer to various individuals, often of European origin, and can appear with different capitalization or spacing variants.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: De Ross
Target entity description: De Ross is a surname that may refer to various individuals, often of European origin, and can appear with different capitalization or spacing variants.
  • A. Roos
    Roos is a variant of the name Rose, often used as a given name or surname in various European languages.
  • B. Roos
    The Roos are the athletic teams representing the University of Missouri–Kansas City in NCAA competition.
  • C. Roos
    Roos is the common nickname for the North Melbourne Football Club, an Australian rules football team in the Australian Football League.
  • D. Mollerussa
    Mollerussa is a small town in the province of Lleida, Catalonia, Spain, known for its agricultural surroundings and regional commercial services.
  • E. Ballaison
    Ballaison is a small commune in the Haute-Savoie department of southeastern France, near the Swiss border and Lake Geneva.
  • 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_69d8838a41f08190b0c3f79c47df5078 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e378ea4b848190bf7c95dad8a855f0 completed April 18, 2026, 12:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a007dc28df48190b01c1328df24df60 completed May 10, 2026, 12:44 p.m.
NEDg Description generation batch_6a007e8cff9881908c6b86da38fc2f08 completed May 10, 2026, 12:48 p.m.
NED2 Entity disambiguation (via description) batch_6a007f53918481908d84ecf50a562266 completed May 10, 2026, 12:51 p.m.
Created at: April 10, 2026, 5:17 a.m.