Triple

T20022998
Position Surface form Disambiguated ID Type / Status
Subject Epistolario E494907 entity
Predicate documentsActivityOf P82572 FINISHED
Object Coluccio Salutati as chancellor of Florence LITERAL 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: Coluccio Salutati as chancellor of Florence | Statement: [Epistolario, documentsActivityOf, Coluccio Salutati as chancellor of Florence]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: documentsActivityOf
Context triple: [Epistolario, documentsActivityOf, Coluccio Salutati as chancellor of Florence]
  • A. documentsActivity chosen
    Indicates that one entity records, describes, or provides evidence of an activity performed by another entity.
  • B. documentsNow
    Indicates that an entity is currently documenting, recording, or writing about another entity at the present time.
  • C. documentList
    Indicates a relationship where one entity serves as a list or collection of documents associated with another entity.
  • D. documentsCommunity
    Indicates that an entity records, describes, or provides information about a particular community.
  • E. documentsJourneyTo
    Indicates that one entity records or describes the travel, route, or progression of another entity from one place or state to another.
  • F. None of above.

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_69da626bfd288190aa5d65098b6433ae completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6628a1ecc8190bf6ee0bedb61e0b8 completed April 20, 2026, 5:29 p.m.
PD Predicate disambiguation batch_69e54ce752748190a0a1ffddd0372271 completed April 19, 2026, 9:45 p.m.
Created at: April 11, 2026, 3:35 p.m.