Triple

T12426221
Position Surface form Disambiguated ID Type / Status
Subject A Running Duck E296903 entity
Predicate author P4 FINISHED
Object Paula Gosling E296903 NE FINISHED

How this triple was built (2 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: Paula Gosling | Statement: [A Running Duck, author, Paula Gosling]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paula Gosling
Context triple: [A Running Duck, author, Paula Gosling]
  • A. Paula Gosling chosen
    Paula Gosling is a British-American crime novelist best known for her suspenseful thrillers, including the novel that inspired the film "Cobra."
  • B. Vivienne Marcheline Jolie-Pitt
    Vivienne Marcheline Jolie-Pitt is the daughter of actors Angelina Jolie and Brad Pitt, known publicly as one of their youngest children.
  • C. Eliza McCartney
    Eliza McCartney is a New Zealand pole vaulter who won a bronze medal at the 2016 Rio Olympics and has held multiple national records in the event.
  • D. Lisa Marie Kurbikoff
    Lisa Marie Kurbikoff is an American photographer and occasional actress known for her work in film and celebrity portraiture.
  • E. Esmeralda Amada Gosling
    Esmeralda Amada Gosling is the eldest daughter of actors Ryan Gosling and Eva Mendes, known primarily for her parents' high-profile Hollywood careers and their efforts to keep her life private.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d6ada0640c81908c061d7fb3d47786 completed April 8, 2026, 7:33 p.m.
NER Named-entity recognition batch_69d94d7ccda08190be2ff1739c1c6855 completed April 10, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69f63f0265fc81909a6288d11b78c2f9 completed May 2, 2026, 6:14 p.m.
Created at: April 8, 2026, 9:55 p.m.