Triple

T23205099
Position Surface form Disambiguated ID Type / Status
Subject Adela of France E580429 entity
Predicate givenName P17 FINISHED
Object Adela NE NERFINISHED

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: Adela | Statement: [Adela of France, givenName, Adela]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Adela
Context triple: [Adela of France, givenName, Adela]
  • A. Adela
    Adela is the rebellious youngest daughter in Federico García Lorca’s play "The House of Bernarda Alba," whose defiance against her oppressive mother drives the tragedy.
  • B. Adela chosen
    Adela was a Norman noblewoman, daughter of William the Conqueror and wife of Stephen, Count of Blois, known for her political influence and piety in medieval Europe.
  • C. Adelina
    Adelina is the central female protagonist in the Italian film "Yesterday, Today and Tomorrow," portrayed in one of the movie’s three episodic stories.
  • D. Adelia
    Adelia is a feminine given name of Latin origin, often considered a variant of Adela and associated with meanings related to nobility.
  • E. Dalila Bela
    Dalila Bela is a Canadian actress best known for her role as Diana Barry in the television series "Anne with an E."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e24602ae1481908aaa6bc7ca493867 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f1907c1d7c8190aca252a39ae0da86 completed April 29, 2026, 5 a.m.
Created at: April 17, 2026, 4:07 p.m.