Triple

T1017273
Position Surface form Disambiguated ID Type / Status
Subject Stephen I of Hungary E21958 entity
Predicate mother P120 FINISHED
Object Sarolt
Sarolt was a prominent 10th-century Hungarian noblewoman and duchess, influential in the Christianization and early state formation of Hungary as the wife of Grand Prince Géza and mother of King Stephen I.
 E129719 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: Sarolt | Statement: [Stephen I of Hungary, mother, Sarolt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Sarolt
Context triple: [Stephen I of Hungary, mother, Sarolt]
  • A. Pál
    Pál is a Hungarian given name, equivalent to the English name Paul.
  • B. István
    István is the Hungarian given name of Stephen I of Hungary, the first Christian king and founder of the medieval Hungarian state.
  • C. Massandra
    Massandra is a resort settlement near Yalta in Crimea, best known for its historic winery and palace.
  • D. Kritzinger
    Kritzinger is a German surname most notably associated with Friedrich Wilhelm Kritzinger, a high-ranking Nazi official involved in the administrative planning of the Holocaust.
  • E. Alfréd
    Alfréd is a given name, primarily used in Hungarian and other Central European languages, that is a variant of the name Alfred.
  • 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: Sarolt
Triple: [Stephen I of Hungary, mother, Sarolt]
Generated description
Sarolt was a prominent 10th-century Hungarian noblewoman and duchess, influential in the Christianization and early state formation of Hungary as the wife of Grand Prince Géza and mother of King Stephen I.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Sarolt
Target entity description: Sarolt was a prominent 10th-century Hungarian noblewoman and duchess, influential in the Christianization and early state formation of Hungary as the wife of Grand Prince Géza and mother of King Stephen I.
  • A. Pál
    Pál is a Hungarian given name, equivalent to the English name Paul.
  • B. István
    István is the Hungarian given name of Stephen I of Hungary, the first Christian king and founder of the medieval Hungarian state.
  • C. Massandra
    Massandra is a resort settlement near Yalta in Crimea, best known for its historic winery and palace.
  • D. Kritzinger
    Kritzinger is a German surname most notably associated with Friedrich Wilhelm Kritzinger, a high-ranking Nazi official involved in the administrative planning of the Holocaust.
  • E. Alfréd
    Alfréd is a given name, primarily used in Hungarian and other Central European languages, that is a variant of the name Alfred.
  • 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_69a493c68e24819080ed0ee8bcfd5ce0 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b7c4d488819081d8214ba0a22fe5 completed March 1, 2026, 10:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac59978cb4819098118b6348b8a55a completed March 7, 2026, 5 p.m.
NEDg Description generation batch_69ac5aad04f48190b04a57eeb9f83a18 completed March 7, 2026, 5:04 p.m.
NED2 Entity disambiguation (via description) batch_69ac5b0ff7708190b8b69e06f11b83d7 completed March 7, 2026, 5:06 p.m.
Created at: March 1, 2026, 7:41 p.m.