Triple

T12415569
Position Surface form Disambiguated ID Type / Status
Subject Ivan Shishman E296626 entity
Predicate mother P120 FINISHED
Object Sarah-Theodora
Sarah-Theodora was a Bulgarian empress (tsaritsa) of the Second Bulgarian Empire and the mother of Tsar Ivan Shishman.
E981211 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: Sarah-Theodora | Statement: [Ivan Shishman, mother, Sarah-Theodora]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sarah-Theodora
Context triple: [Ivan Shishman, mother, Sarah-Theodora]
  • A. Christina Alexandra
    Christina Alexandra, better known as Queen Christina of Sweden, was a 17th-century Swedish monarch renowned for her intellectual pursuits, unconventional lifestyle, and abdication of the throne.
  • B. Eleanor
    Eleanor is a feminine given name most famously borne by Eleanor Roosevelt, the influential First Lady of the United States and human rights advocate.
  • C. Eleanor
    Eleanor was one of the merchant ships in Boston Harbor whose tea cargo was destroyed during the Boston Tea Party protest against British taxation in 1773.
  • D. Anne
    Anne is the birth name of Nancy Reagan, the former First Lady of the United States and wife of President Ronald Reagan.
  • E. Anne
    Anne was the Queen of Great Britain and Ireland from 1702 to 1714, the last monarch of the House of Stuart.
  • 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: Sarah-Theodora
Triple: [Ivan Shishman, mother, Sarah-Theodora]
Generated description
Sarah-Theodora was a Bulgarian empress (tsaritsa) of the Second Bulgarian Empire and the mother of Tsar Ivan Shishman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sarah-Theodora
Target entity description: Sarah-Theodora was a Bulgarian empress (tsaritsa) of the Second Bulgarian Empire and the mother of Tsar Ivan Shishman.
  • A. Christina Alexandra
    Christina Alexandra, better known as Queen Christina of Sweden, was a 17th-century Swedish monarch renowned for her intellectual pursuits, unconventional lifestyle, and abdication of the throne.
  • B. Eleanor
    Eleanor is a feminine given name most famously borne by Eleanor Roosevelt, the influential First Lady of the United States and human rights advocate.
  • C. Eleanor
    Eleanor was one of the merchant ships in Boston Harbor whose tea cargo was destroyed during the Boston Tea Party protest against British taxation in 1773.
  • D. Anne
    Anne was the Queen of Great Britain and Ireland from 1702 to 1714, the last monarch of the House of Stuart.
  • E. Anne
    Anne is the birth name of Nancy Reagan, the former First Lady of the United States and wife of President Ronald Reagan.
  • 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_69d6ad9f464c81909db36d7e96e34b9e completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d6c4f6c8190bc99d3f7b64205c3 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f634915940819092665f1f35aa823d completed May 2, 2026, 5:29 p.m.
NEDg Description generation batch_69f635997b088190b6207fcac5594eb2 completed May 2, 2026, 5:34 p.m.
NED2 Entity disambiguation (via description) batch_69f636d9e13881908d3d08c6cf954304 completed May 2, 2026, 5:39 p.m.
Created at: April 8, 2026, 9:55 p.m.