Triple

T1234761
Position Surface form Disambiguated ID Type / Status
Subject Sigrid Undset E26522 entity
Predicate familyName P18 FINISHED
Object Undset
Undset is the surname of Sigrid Undset, the Norwegian novelist and Nobel Prize in Literature laureate renowned for her medieval trilogy "Kristin Lavransdatter."
E141112 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: Undset | Statement: [Sigrid Undset, familyName, Undset]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Undset
Context triple: [Sigrid Undset, familyName, Undset]
  • A. Tullistes
    Tullistes are the inhabitants of the French city of Tulle, located in the Corrèze department in central France.
  • B. The Pleased
    The Pleased was an indie rock band from San Francisco known for featuring harpist-singer-songwriter Joanna Newsom as a member early in her career.
  • C. Den Osse
    Den Osse is a small Dutch coastal village and marina resort on the Grevelingenmeer, known for water sports, diving, and recreational tourism.
  • D. Thussu
    Thussu is an Indian family name associated with individuals such as Swarup Rani Thussu.
  • E. Les Solitudes
    Les Solitudes is a reflective poetic work by French writer and first Nobel Prize in Literature laureate Sully Prudhomme, exploring themes of isolation and inner life.
  • 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: Undset
Triple: [Sigrid Undset, familyName, Undset]
Generated description
Undset is the surname of Sigrid Undset, the Norwegian novelist and Nobel Prize in Literature laureate renowned for her medieval trilogy "Kristin Lavransdatter."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Undset
Target entity description: Undset is the surname of Sigrid Undset, the Norwegian novelist and Nobel Prize in Literature laureate renowned for her medieval trilogy "Kristin Lavransdatter."
  • A. Tullistes
    Tullistes are the inhabitants of the French city of Tulle, located in the Corrèze department in central France.
  • B. The Pleased
    The Pleased was an indie rock band from San Francisco known for featuring harpist-singer-songwriter Joanna Newsom as a member early in her career.
  • C. Den Osse
    Den Osse is a small Dutch coastal village and marina resort on the Grevelingenmeer, known for water sports, diving, and recreational tourism.
  • D. Thussu
    Thussu is an Indian family name associated with individuals such as Swarup Rani Thussu.
  • E. Les Solitudes
    Les Solitudes is a reflective poetic work by French writer and first Nobel Prize in Literature laureate Sully Prudhomme, exploring themes of isolation and inner life.
  • 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_69a4948571c88190a9191e451e6035fd completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be5e421081908f2432528019db25 completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac8a16badc8190b5b603db0ca738cb completed March 7, 2026, 8:27 p.m.
NEDg Description generation batch_69ac8b70bd888190bed944579237bfad completed March 7, 2026, 8:32 p.m.
NED2 Entity disambiguation (via description) batch_69ac8bce4be48190b7e396d31e881450 completed March 7, 2026, 8:34 p.m.
Created at: March 1, 2026, 7:47 p.m.