Triple

T22750870
Position Surface form Disambiguated ID Type / Status
Subject Charles Sellon E562691 entity
Predicate familyName P18 FINISHED
Object Sellon
Sellon is a surname most notably associated with American character actor Charles Sellon, who appeared in early 20th-century stage and film productions.
 E1551576 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: Sellon | Statement: [Charles Sellon, familyName, Sellon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sellon
Context triple: [Charles Sellon, familyName, Sellon]
  • A. Saleen
    Saleen is an American high-performance sports car manufacturer best known for producing powerful, limited-production supercars and racing vehicles.
  • B. Saleen
    Saleen is a small village in County Cork, Ireland, situated in the East Cork region.
  • C. Solvan
    Solvan is a river associated with the town of Lons-le-Saunier in the Jura department of eastern France.
  • D. Sellia
    Sellia is a small village in Crete, Greece, known for its traditional Cretan character and scenic rural surroundings.
  • E. Loxa
    Loxa is the historical name of the Ecuadorian city now known as Loja, an important cultural and musical center in the country's southern Andes.
  • 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: Sellon
Triple: [Charles Sellon, familyName, Sellon]
Generated description
Sellon is a surname most notably associated with American character actor Charles Sellon, who appeared in early 20th-century stage and film productions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sellon
Target entity description: Sellon is a surname most notably associated with American character actor Charles Sellon, who appeared in early 20th-century stage and film productions.
  • A. Saleen
    Saleen is an American high-performance sports car manufacturer best known for producing powerful, limited-production supercars and racing vehicles.
  • B. Saleen
    Saleen is a small village in County Cork, Ireland, situated in the East Cork region.
  • C. Solvan
    Solvan is a river associated with the town of Lons-le-Saunier in the Jura department of eastern France.
  • D. Sellia
    Sellia is a small village in Crete, Greece, known for its traditional Cretan character and scenic rural surroundings.
  • E. Loxa
    Loxa is the historical name of the Ecuadorian city now known as Loja, an important cultural and musical center in the country's southern Andes.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179b9ac348190bff4dc470931f7e3 completed April 29, 2026, 3:23 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b8fd7d2388190964a84175f034f8b completed May 18, 2026, 10:16 p.m.
NEDg Description generation batch_6a0b905d3ba48190bf73b2334b6ef3a6 completed May 18, 2026, 10:19 p.m.
NED2 Entity disambiguation (via description) batch_6a0b90c481cc8190acdffb0c341998ea completed May 18, 2026, 10:20 p.m.
Created at: April 17, 2026, 3:24 p.m.