Triple

T11037115
Position Surface form Disambiguated ID Type / Status
Subject Salvation E260913 entity
Predicate portrayedBy P1507 FINISHED
Object Melia Kreiling
Melia Kreiling is a Greek-British actress known for her roles in television series such as "Salvation" and appearances in films including "Guardians of the Galaxy."
 E900719 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: Melia Kreiling | Statement: [Salvation, portrayedBy, Melia Kreiling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Melia Kreiling
Context triple: [Salvation, portrayedBy, Melia Kreiling]
  • A. Maria Ricossa
    Maria Ricossa is a Canadian actress known for her work in film, television, and theatre.
  • B. Clotilde Narcis
    Clotilde Narcis was the wife and muse of French sculptor Aristide Maillol, known primarily through her close association with his life and work.
  • C. Marta Linden
    Marta Linden was an American film actress active in the 1930s and 1940s, known for supporting roles in Hollywood studio productions.
  • D. Lelia
    Lelia is the given name of A'Lelia Walker, an influential African-American businesswoman and patron of the arts during the Harlem Renaissance.
  • E. Maria Fitel
    Maria Fitel is an alumna of the private Lakeside School in Seattle, known for educating many prominent figures in technology and business.
  • 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: Melia Kreiling
Triple: [Salvation, portrayedBy, Melia Kreiling]
Generated description
Melia Kreiling is a Greek-British actress known for her roles in television series such as "Salvation" and appearances in films including "Guardians of the Galaxy."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Melia Kreiling
Target entity description: Melia Kreiling is a Greek-British actress known for her roles in television series such as "Salvation" and appearances in films including "Guardians of the Galaxy."
  • A. Maria Ricossa
    Maria Ricossa is a Canadian actress known for her work in film, television, and theatre.
  • B. Clotilde Narcis
    Clotilde Narcis was the wife and muse of French sculptor Aristide Maillol, known primarily through her close association with his life and work.
  • C. Marta Linden
    Marta Linden was an American film actress active in the 1930s and 1940s, known for supporting roles in Hollywood studio productions.
  • D. Lelia
    Lelia is the given name of A'Lelia Walker, an influential African-American businesswoman and patron of the arts during the Harlem Renaissance.
  • E. Maria Fitel
    Maria Fitel is an alumna of the private Lakeside School in Seattle, known for educating many prominent figures in technology and business.
  • 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_69d6aa979bdc8190bf0e79104cc098c1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797fd5fe081908af13835b18de7b8 completed April 9, 2026, 12:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3a9c669608190af97c461beaf9f31 completed April 18, 2026, 3:56 p.m.
NEDg Description generation batch_69e3ad00b5c08190a7bf3ecbeae76d88 completed April 18, 2026, 4:10 p.m.
NED2 Entity disambiguation (via description) batch_69e3b1fff754819092d634f46fb42387 completed April 18, 2026, 4:32 p.m.
Created at: April 8, 2026, 9:25 p.m.