Triple

T13865097
Position Surface form Disambiguated ID Type / Status
Subject King Milutin of Serbia E333301 entity
Predicate spouse P13 FINISHED
Object Ana Terter
Ana Terter was a medieval Bulgarian princess who became Queen consort of Serbia through her marriage to King Stefan Milutin.
 E1066203 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: Ana Terter | Statement: [King Milutin of Serbia, spouse, Ana Terter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ana Terter
Context triple: [King Milutin of Serbia, spouse, Ana Terter]
  • A. Ana Leza
    Ana Leza is a Spanish actress best known for her work in film and television in the 1980s and 1990s and for her former marriage to actor Antonio Banderas.
  • B. Iola Tornagi
    Iola Tornagi was the wife of renowned Russian opera bass Feodor Chaliapin and a figure associated with his personal and artistic life.
  • C. Corina
    Corina is a feminine given name used in various cultures, often considered a variant of names like Corine or Corinna.
  • D. Teressa
    Teressa is a Nicobarese language variety spoken by the indigenous community on Teressa Island in India’s Nicobar archipelago.
  • E. Arleta
    Arleta is a residential neighborhood in the San Fernando Valley region of Los Angeles, California.
  • 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: Ana Terter
Triple: [King Milutin of Serbia, spouse, Ana Terter]
Generated description
Ana Terter was a medieval Bulgarian princess who became Queen consort of Serbia through her marriage to King Stefan Milutin.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ana Terter
Target entity description: Ana Terter was a medieval Bulgarian princess who became Queen consort of Serbia through her marriage to King Stefan Milutin.
  • A. Ana Leza
    Ana Leza is a Spanish actress best known for her work in film and television in the 1980s and 1990s and for her former marriage to actor Antonio Banderas.
  • B. Iola Tornagi
    Iola Tornagi was the wife of renowned Russian opera bass Feodor Chaliapin and a figure associated with his personal and artistic life.
  • C. Corina
    Corina is a feminine given name used in various cultures, often considered a variant of names like Corine or Corinna.
  • D. Teressa
    Teressa is a Nicobarese language variety spoken by the indigenous community on Teressa Island in India’s Nicobar archipelago.
  • E. Arleta
    Arleta is a residential neighborhood in the San Fernando Valley region of Los Angeles, California.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c30d9c81908217d41a3b4aaf85 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c10113288190b799126d934df92a completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c1e7efd88190ac07472647da69e7 completed May 3, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_69f7c3396f7c8190987079bf24ac8695 completed May 3, 2026, 9:50 p.m.
Created at: April 9, 2026, 10:14 p.m.