Triple

T12366175
Position Surface form Disambiguated ID Type / Status
Subject Blu E294875 entity
Predicate owner P347 FINISHED
Object Linda Gunderson E525691 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: Linda Gunderson | Statement: [Blu, owner, Linda Gunderson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Linda Gunderson
Context triple: [Blu, owner, Linda Gunderson]
  • A. Linda Gunderson chosen
    Linda Gunderson is a kind-hearted Minnesota bookshop owner who becomes the human protagonist and caretaker of the rare macaw Blu in the animated film "Rio."
  • B. Linda Nordley
    Linda Nordley is a central female character in the 1953 adventure film "Mogambo," portrayed as a refined Englishwoman whose arrival complicates the romantic and emotional dynamics on an African safari.
  • C. Linda Gilbert
    Linda Gilbert is known for being the first wife of American actor David Carradine, whom she married in the 1960s.
  • D. Linda Larkin
    Linda Larkin is an American actress best known for providing the speaking voice of Princess Jasmine in Disney’s animated film "Aladdin" and its related media.
  • E. Linda Wallem
    Linda Wallem is an American television writer, producer, and actress best known for co-creating the acclaimed medical dramedy series "Nurse Jackie."
  • 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_69d6ab6d8a4081908636601e69ddf262 completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d93fa502988190ba170dee90d9f394 completed April 10, 2026, 6:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffa92635b08190a333702bec5b94e9 completed May 9, 2026, 9:37 p.m.
Created at: April 8, 2026, 9:54 p.m.