Triple

T4560425
Position Surface form Disambiguated ID Type / Status
Subject Konstantin Stanislavski E120576 entity
Predicate spouse P13 FINISHED
Object Maria Lilina
Maria Lilina was a prominent Russian stage actress of the Moscow Art Theatre and the wife and close artistic collaborator of theatre director Konstantin Stanislavski.
 E452536 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: Maria Lilina | Statement: [Konstantin Stanislavski, spouse, Maria Lilina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maria Lilina
Context triple: [Konstantin Stanislavski, spouse, Maria Lilina]
  • A. Caitlyn
    Caitlyn is the given name of Caitlyn Jenner, the American television personality and former Olympic gold medal–winning decathlete.
  • B. Katarina
    Katarina is a feminine given name, commonly used in various European cultures, that is a variant of the name Catherine.
  • C. Leona
    Leona is a feminine given name used in various cultures, often derived from the Latin word for "lion."
  • D. Tristana
    Tristana is a 1970 Spanish drama film directed by Luis Buñuel, known for its exploration of power, morality, and desire through the story of a young woman and her older guardian.
  • E. D.Va
    D.Va is a popular hero from the game Overwatch, known as a former pro gamer who pilots a high-tech mech in fast-paced combat.
  • 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: Maria Lilina
Triple: [Konstantin Stanislavski, spouse, Maria Lilina]
Generated description
Maria Lilina was a prominent Russian stage actress of the Moscow Art Theatre and the wife and close artistic collaborator of theatre director Konstantin Stanislavski.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maria Lilina
Target entity description: Maria Lilina was a prominent Russian stage actress of the Moscow Art Theatre and the wife and close artistic collaborator of theatre director Konstantin Stanislavski.
  • A. Caitlyn
    Caitlyn is the given name of Caitlyn Jenner, the American television personality and former Olympic gold medal–winning decathlete.
  • B. Katarina
    Katarina is a feminine given name, commonly used in various European cultures, that is a variant of the name Catherine.
  • C. Leona
    Leona is a feminine given name used in various cultures, often derived from the Latin word for "lion."
  • D. Tristana
    Tristana is a 1970 Spanish drama film directed by Luis Buñuel, known for its exploration of power, morality, and desire through the story of a young woman and her older guardian.
  • E. D.Va
    D.Va is a popular hero from the game Overwatch, known as a former pro gamer who pilots a high-tech mech in fast-paced combat.
  • 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_69bd4636f1648190a701445c2fcd9c17 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd582b871c8190be0b70c76d639000 completed March 20, 2026, 2:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdc59b2514819091f3845307cb1c8b completed March 20, 2026, 10:09 p.m.
NEDg Description generation batch_69bdc66a981c8190a472722af45ce023 completed March 20, 2026, 10:12 p.m.
NED2 Entity disambiguation (via description) batch_69bdc6de076081909d2ad276cc7a1141 completed March 20, 2026, 10:14 p.m.
Created at: March 20, 2026, 1:09 p.m.