Triple

T8241620
Position Surface form Disambiguated ID Type / Status
Subject Benedetta E192548 entity
Predicate relatedName P3889 FINISHED
Object Benedicta E721607 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: Benedicta | Statement: [Benedetta, relatedName, Benedicta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Benedicta
Context triple: [Benedetta, relatedName, Benedicta]
  • A. Benedicta chosen
    Benedicta is a feminine given name, often considered a variant of Benedetta, used in various European cultures.
  • B. Ermentrud
    Ermentrud is a given name, typically a historical or medieval European female name, that serves as a variant form of Ermintrude.
  • C. Bernardine
    Bernardine is a 1957 musical comedy film starring Pat Boone in one of his early leading screen roles.
  • D. Eulalia Callis
    Eulalia Callis was the wife of Spanish military officer and early California colonial governor Pedro Fages, making her one of the notable women connected to the early Spanish colonial period in Alta California.
  • E. Agnese
    Agnese is an Italian given name, equivalent to the English name Agnes, traditionally associated with Christian saints and classical European usage.
  • 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_69ca82dc8f148190a2c75a98501a7b91 completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb783f67708190a4e1c4078c3a6fb0 completed March 31, 2026, 7:31 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd6801eaec8190a104ac6b08030376 completed April 1, 2026, 6:46 p.m.
Created at: March 30, 2026, 5:47 p.m.