Triple

T774919
Position Surface form Disambiguated ID Type / Status
Subject Ingrid Bergman E16365 entity
Predicate child P120 FINISHED
Object Pia Lindström
Pia Lindström is a Swedish-American television journalist and critic, best known as the eldest daughter of legendary actress Ingrid Bergman.
E92342 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: Pia Lindström | Statement: [Ingrid Bergman, child, Pia Lindström]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pia Lindström
Context triple: [Ingrid Bergman, child, Pia Lindström]
  • A. Therese Andersson
    Therese Andersson is known as the wife of former Swedish NHL star goaltender Henrik Lundqvist.
  • B. Hanna Alström
    Hanna Alström is a Swedish actress best known internationally for her role as Princess Tilde in the action-comedy film "Kingsman: The Secret Service" and its sequel.
  • C. Beata Ernman
    Beata Ernman is a Swedish opera singer and author, known as the mother of climate activist Greta Thunberg and co-writer of the family memoir "Our House Is on Fire."
  • D. Cecilia Nessen
    Cecilia Nessen is a film producer best known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
  • E. Nina Agdal
    Nina Agdal is a Danish fashion model best known for her work with Sports Illustrated Swimsuit Issue and major international advertising campaigns.
  • 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: Pia Lindström
Triple: [Ingrid Bergman, child, Pia Lindström]
Generated description
Pia Lindström is a Swedish-American television journalist and critic, best known as the eldest daughter of legendary actress Ingrid Bergman.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pia Lindström
Target entity description: Pia Lindström is a Swedish-American television journalist and critic, best known as the eldest daughter of legendary actress Ingrid Bergman.
  • A. Therese Andersson
    Therese Andersson is known as the wife of former Swedish NHL star goaltender Henrik Lundqvist.
  • B. Hanna Alström
    Hanna Alström is a Swedish actress best known internationally for her role as Princess Tilde in the action-comedy film "Kingsman: The Secret Service" and its sequel.
  • C. Beata Ernman
    Beata Ernman is a Swedish opera singer and author, known as the mother of climate activist Greta Thunberg and co-writer of the family memoir "Our House Is on Fire."
  • D. Cecilia Nessen
    Cecilia Nessen is a film producer best known for her work on the documentary "I Am Greta," which follows climate activist Greta Thunberg.
  • E. Nina Agdal
    Nina Agdal is a Danish fashion model best known for her work with Sports Illustrated Swimsuit Issue and major international advertising campaigns.
  • 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_69a49369a0848190af883934cee3db4c completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a73236288190b82d66202f2f7399 completed March 1, 2026, 8:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69a66d9b8b308190b19378e797f499b1 completed March 3, 2026, 5:11 a.m.
NEDg Description generation batch_69a66f2fb9a081908de794b20b6451b6 completed March 3, 2026, 5:18 a.m.
NED2 Entity disambiguation (via description) batch_69a66fcc9208819082e7fd20f991622c completed March 3, 2026, 5:21 a.m.
Created at: March 1, 2026, 7:37 p.m.