Triple

T408988
Position Surface form Disambiguated ID Type / Status
Subject Saint Barbara E9444 entity
Predicate legend P11062 FINISHED
Object kept in a tower by her pagan father 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: kept in a tower by her pagan father | Statement: [Saint Barbara, legend, kept in a tower by her pagan father]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: legend
Context triple: [Saint Barbara, legend, kept in a tower by her pagan father]
  • A. lays
    Indicates that one entity deposits or places something, typically eggs or objects, onto a surface or in a location.
  • B. title
    Indicates that one entity serves as the formal name or designation of another entity.
  • C. flag
    Indicates that one entity marks, signals, or draws attention to another entity, often to denote status, importance, or the need for review or action.
  • D. badge
    Indicates that one entity confers, displays, or is associated with a symbolic mark or emblem representing status, achievement, role, or affiliation in relation to another entity.
  • E. legacyGoal
    Indicates that an entity has a long-term, enduring objective or impact it aims to leave behind beyond its immediate actions or existence.
  • F. None of above. chosen

Provenance (4 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_69a2e80111fc8190961d5b7c6154123f completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ecc098c4819088d127c5ea55ced9 completed Feb. 28, 2026, 1:25 p.m.
PD Predicate disambiguation batch_69a2e971a3a481909e6b075f25dd234a completed Feb. 28, 2026, 1:11 p.m.
PDg Predicate description generation batch_69a2ea4545608190898436c72e10f39d completed Feb. 28, 2026, 1:14 p.m.
Created at: Feb. 28, 2026, 1:08 p.m.