Triple

T1431173
Position Surface form Disambiguated ID Type / Status
Subject Audrey Hepburn E30448 entity
Predicate notableWork P4 FINISHED
Object Ondine
Ondine is a 1954 Broadway play by Jean Giraudoux, adapted by Maurice Valency, in which Audrey Hepburn gave an acclaimed, Tony-winning performance as a water nymph.
 E163731 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: Ondine | Statement: [Audrey Hepburn, notableWork, Ondine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Ondine
Context triple: [Audrey Hepburn, notableWork, Ondine]
  • A. Ondine
    Ondine is a Finnish classical music record label renowned for high-quality recordings of Nordic and contemporary repertoire.
  • B. Ondine
    Ondine is a character from the "Tar Baby" narrative, often associated with themes of entrapment and trickery rooted in African American folklore.
  • C. Lenore
    "Lenore" is a melancholic poem by Edgar Allan Poe that explores themes of death, mourning, and idealized love through the lament for a lost woman.
  • D. Cecilia
    Cecilia is a feminine given name of Latin origin, traditionally associated with Saint Cecilia, the patron saint of music.
  • E. Annabella
    Annabella was a French film actress of the 1930s and 1940s, known for her work in both European and Hollywood cinema.
  • 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: Ondine
Triple: [Audrey Hepburn, notableWork, Ondine]
Generated description
Ondine is a 1954 Broadway play by Jean Giraudoux, adapted by Maurice Valency, in which Audrey Hepburn gave an acclaimed, Tony-winning performance as a water nymph.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Ondine
Target entity description: Ondine is a 1954 Broadway play by Jean Giraudoux, adapted by Maurice Valency, in which Audrey Hepburn gave an acclaimed, Tony-winning performance as a water nymph.
  • A. Ondine
    Ondine is a Finnish classical music record label renowned for high-quality recordings of Nordic and contemporary repertoire.
  • B. Ondine
    Ondine is a character from the "Tar Baby" narrative, often associated with themes of entrapment and trickery rooted in African American folklore.
  • C. Lenore
    "Lenore" is a melancholic poem by Edgar Allan Poe that explores themes of death, mourning, and idealized love through the lament for a lost woman.
  • D. Cecilia
    Cecilia is a feminine given name of Latin origin, traditionally associated with Saint Cecilia, the patron saint of music.
  • E. Annabella
    Annabella was a French film actress of the 1930s and 1940s, known for her work in both European and Hollywood cinema.
  • 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_69a498fc69ec8190b61722bd4b67c4d2 completed March 1, 2026, 7:52 p.m.
NER Named-entity recognition batch_69a4c4dc3e2081909ff951fe73db277b completed March 1, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad016bf2608190a675cbd42e474082 completed March 8, 2026, 4:56 a.m.
NEDg Description generation batch_69ad0294353081908e29735d1b83f2cc completed March 8, 2026, 5:01 a.m.
NED2 Entity disambiguation (via description) batch_69ad02f6bf288190bcb785762d14787c completed March 8, 2026, 5:02 a.m.
Created at: March 1, 2026, 8 p.m.