Triple

T5549247
Position Surface form Disambiguated ID Type / Status
Subject Sonja Haraldsen E145484 entity
Predicate givenName P17 FINISHED
Object Sonja
Sonja is the Queen of Norway, married to King Harald V and known for her long-standing role in the Norwegian royal family.
E532728 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: Sonja | Statement: [Sonja Haraldsen, givenName, Sonja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sonja
Context triple: [Sonja Haraldsen, givenName, Sonja]
  • A. Sonja Zat
    Sonja Zat is the central protagonist of the film "Lantana," around whom the story’s emotional and narrative tensions revolve.
  • B. Sonia
    Sonia is a central female character in the romantic comedy film "Think Like a Man," whose relationships and personal growth intersect with the movie’s ensemble cast and themes about modern dating.
  • C. Sonia
    Sonia is the given name of Sonia Gandhi, an Italian-born Indian politician and former president of the Indian National Congress.
  • D. Sonja Harper
    Sonja Harper is a teenage granddaughter in the sitcom "Mama’s Family," known for her rebellious streak and frequent clashes with her sharp-tongued grandmother, Thelma Harper.
  • E. Sondra
    Sondra is a feminine given name, often considered a variant of Sandra or Alexandra.
  • 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: Sonja
Triple: [Sonja Haraldsen, givenName, Sonja]
Generated description
Sonja is the Queen of Norway, married to King Harald V and known for her long-standing role in the Norwegian royal family.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sonja
Target entity description: Sonja is the Queen of Norway, married to King Harald V and known for her long-standing role in the Norwegian royal family.
  • A. Sonja Zat
    Sonja Zat is the central protagonist of the film "Lantana," around whom the story’s emotional and narrative tensions revolve.
  • B. Sonia
    Sonia is a central female character in the romantic comedy film "Think Like a Man," whose relationships and personal growth intersect with the movie’s ensemble cast and themes about modern dating.
  • C. Sonia
    Sonia is the given name of Sonia Gandhi, an Italian-born Indian politician and former president of the Indian National Congress.
  • D. Sonja Harper
    Sonja Harper is a teenage granddaughter in the sitcom "Mama’s Family," known for her rebellious streak and frequent clashes with her sharp-tongued grandmother, Thelma Harper.
  • E. Sondra
    Sondra is a feminine given name, often considered a variant of Sandra or Alexandra.
  • 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_69c008fb879c81909f5bfa56fadc1d46 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01fe143ec8190bb67d2530c92a419 completed March 22, 2026, 4:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0282dd7408190ad762fca9ff5e04b completed March 22, 2026, 5:34 p.m.
NEDg Description generation batch_69c0400d14cc8190a9962cb43fe17d83 completed March 22, 2026, 7:16 p.m.
NED2 Entity disambiguation (via description) batch_69c0407964d08190b5552b410c9ba915 completed March 22, 2026, 7:18 p.m.
Created at: March 22, 2026, 3:35 p.m.