Triple

T17273207
Position Surface form Disambiguated ID Type / Status
Subject Heidi (1968 film) E419316 entity
Predicate title P38 FINISHED
Object Heidi
Heidi is a 1968 made-for-television film adaptation of Johanna Spyri’s classic novel about an orphaned Swiss girl and her life in the Alps.
 E1300836 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: Heidi | Statement: [Heidi (1968 film), title, Heidi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Heidi
Context triple: [Heidi (1968 film), title, Heidi]
  • A. Heidi
    Heidi is the spouse of Bernard "Beanie" Campbell, about whom little public biographical information is widely documented.
  • B. Heidi
    Heidi is a classic 1881 children’s novel by Swiss author Johanna Spyri about an orphan girl growing up in the Swiss Alps, renowned for its themes of nature, innocence, and moral development.
  • C. Heidi
    Heidi is a 2015 family drama film adaptation of Johanna Spyri’s classic Swiss children’s novel about an orphan girl growing up in the Alps.
  • D. Heidi
    Heidi is a play by American playwright Halley Feiffer, known for its darkly comic exploration of complex emotional and familial dynamics.
  • E. Heidi Grows Up
    Heidi Grows Up is a sequel novel to Johanna Spyri’s classic children’s book "Heidi," continuing the story of the Swiss orphan as she grows older and faces new adventures.
  • 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: Heidi
Triple: [Heidi (1968 film), title, Heidi]
Generated description
Heidi is a 1968 made-for-television film adaptation of Johanna Spyri’s classic novel about an orphaned Swiss girl and her life in the Alps.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Heidi
Target entity description: Heidi is a 1968 made-for-television film adaptation of Johanna Spyri’s classic novel about an orphaned Swiss girl and her life in the Alps.
  • A. Heidi
    Heidi is a classic 1881 children’s novel by Swiss author Johanna Spyri about an orphan girl growing up in the Swiss Alps, renowned for its themes of nature, innocence, and moral development.
  • B. Heidi
    Heidi is a play by American playwright Halley Feiffer, known for its darkly comic exploration of complex emotional and familial dynamics.
  • C. Heidi
    Heidi is the spouse of Bernard "Beanie" Campbell, about whom little public biographical information is widely documented.
  • D. Heidi
    Heidi is a 2015 family drama film adaptation of Johanna Spyri’s classic Swiss children’s novel about an orphan girl growing up in the Alps.
  • E. Heidi Grows Up
    Heidi Grows Up is a sequel novel to Johanna Spyri’s classic children’s book "Heidi," continuing the story of the Swiss orphan as she grows older and faces new adventures.
  • 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_69d886da626481908a14ce7830329a35 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42f4b023c8190b92df4015c14c3a8 completed April 19, 2026, 1:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03430a027c8190b5cc71fd18fe9603 completed May 12, 2026, 3:11 p.m.
NEDg Description generation batch_6a03441695948190ba06d4015c219f87 completed May 12, 2026, 3:15 p.m.
NED2 Entity disambiguation (via description) batch_6a03447f873c8190b63c40afb8f055d9 completed May 12, 2026, 3:17 p.m.
Created at: April 10, 2026, 5:40 a.m.