Triple

T2341643
Position Surface form Disambiguated ID Type / Status
Subject Charlemagne E45038 entity
Predicate child P120 FINISHED
Object Gisela
Gisela was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family.
 E260312 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: Gisela | Statement: [Charlemagne, child, Gisela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gisela
Context triple: [Charlemagne, child, Gisela]
  • A. Ricarda
    Ricarda is a feminine given name, primarily used in German- and Spanish-speaking countries, derived from the male name Richard.
  • B. Franziska
    Franziska is a feminine given name of German origin, closely related to and cognate with the name Frances.
  • C. Hedvig
    Hedvig is a Scandinavian female given name, historically borne by several notable women in Swedish and broader Nordic royalty and nobility.
  • D. Dorothee
    Dorothee is a feminine given name, commonly used in German- and French-speaking countries, that is a variant of the name Dorothea.
  • E. Gertrudis
    Gertrudis is a passionate and rebellious sister in "Like Water for Chocolate" whose fiery nature and unconventional choices challenge her family's strict traditions.
  • 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: Gisela
Triple: [Charlemagne, child, Gisela]
Generated description
Gisela was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gisela
Target entity description: Gisela was a daughter of Charlemagne, the Frankish king and first Holy Roman Emperor, and a member of the Carolingian royal family.
  • A. Ricarda
    Ricarda is a feminine given name, primarily used in German- and Spanish-speaking countries, derived from the male name Richard.
  • B. Franziska
    Franziska is a feminine given name of German origin, closely related to and cognate with the name Frances.
  • C. Hedvig
    Hedvig is a Scandinavian female given name, historically borne by several notable women in Swedish and broader Nordic royalty and nobility.
  • D. Dorothee
    Dorothee is a feminine given name, commonly used in German- and French-speaking countries, that is a variant of the name Dorothea.
  • E. Gertrudis
    Gertrudis is a passionate and rebellious sister in "Like Water for Chocolate" whose fiery nature and unconventional choices challenge her family's strict traditions.
  • 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_69a88917935081909b755dbf38e81024 completed March 4, 2026, 7:33 p.m.
NER Named-entity recognition batch_69abc6ad01fc81909e386986e9acc989 completed March 7, 2026, 6:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69aea88113988190b89abfc01f5bf6f4 completed March 9, 2026, 11:01 a.m.
NEDg Description generation batch_69aeaacdb19081908561e845eda30143 completed March 9, 2026, 11:11 a.m.
NED2 Entity disambiguation (via description) batch_69aeab435b7081909ec4815f64fe9ea1 completed March 9, 2026, 11:13 a.m.
Created at: March 4, 2026, 7:52 p.m.