Triple

T13847514
Position Surface form Disambiguated ID Type / Status
Subject Sverre of Norway E332845 entity
Predicate mother P120 FINISHED
Object Gunnhild
Gunnhild was the mother of King Sverre of Norway, a key figure in the country’s medieval royal lineage.
 E1065704 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: Gunnhild | Statement: [Sverre of Norway, mother, Gunnhild]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gunnhild
Context triple: [Sverre of Norway, mother, Gunnhild]
  • A. Thjodhild
    Thjodhild was a Norse woman of the Viking Age, best known as one of the earliest Christian converts in Greenland and for building the first church there.
  • B. Gudrun
    Gudrun was the daughter of Heinrich Himmler, a leading Nazi official, and later became known for her unrepentant support of former SS members after World War II.
  • C. Gudrun
    Gudrun is a tragic heroine from Norse legend, best known as the wife of the dragon-slayer Sigurd and a central figure in the Volsunga saga and related epic tales.
  • D. Gunhild Godwinsdóttir
    Gunhild Godwinsdóttir was a daughter of the powerful Anglo-Danish noblewoman Gytha Thorkelsdóttir and a member of the prominent Godwin family in 11th-century England.
  • E. Ingrith
    Ingrith is a feminine given name, likely a variant of the Scandinavian name Ingrid.
  • 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: Gunnhild
Triple: [Sverre of Norway, mother, Gunnhild]
Generated description
Gunnhild was the mother of King Sverre of Norway, a key figure in the country’s medieval royal lineage.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gunnhild
Target entity description: Gunnhild was the mother of King Sverre of Norway, a key figure in the country’s medieval royal lineage.
  • A. Thjodhild
    Thjodhild was a Norse woman of the Viking Age, best known as one of the earliest Christian converts in Greenland and for building the first church there.
  • B. Gudrun
    Gudrun was the daughter of Heinrich Himmler, a leading Nazi official, and later became known for her unrepentant support of former SS members after World War II.
  • C. Gudrun
    Gudrun is a tragic heroine from Norse legend, best known as the wife of the dragon-slayer Sigurd and a central figure in the Volsunga saga and related epic tales.
  • D. Gunhild Godwinsdóttir
    Gunhild Godwinsdóttir was a daughter of the powerful Anglo-Danish noblewoman Gytha Thorkelsdóttir and a member of the prominent Godwin family in 11th-century England.
  • E. Ingrith
    Ingrith is a feminine given name, likely a variant of the Scandinavian name Ingrid.
  • 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_69d81c5ba13c8190839315f54768acfd completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de02b2a9788190b164760adec64ef6 completed April 14, 2026, 9:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c0f189008190bb9afeef42564a33 completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c23410dc8190972245cecfa85871 completed May 3, 2026, 9:46 p.m.
NED2 Entity disambiguation (via description) batch_69f7c3031a0c8190ad30d59fe1f2322e completed May 3, 2026, 9:49 p.m.
Created at: April 9, 2026, 10:14 p.m.