Triple

T4757793
Position Surface form Disambiguated ID Type / Status
Subject Beatrice E105629 entity
Predicate appearsIn P795 FINISHED
Object Paradiso E108898 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: Paradiso | Statement: [Beatrice, appearsIn, Paradiso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paradiso
Context triple: [Beatrice, appearsIn, Paradiso]
  • A. Paradiso chosen
    Paradiso is the third and final canticle of Dante Alighieri's Divine Comedy, depicting the poet's allegorical journey through the celestial spheres of Heaven toward the vision of God.
  • B. Paradiso
    Paradiso is a picturesque Swiss lakeside town in the canton of Ticino, known for its scenic setting on Lake Lugano and proximity to Monte San Salvatore.
  • C. Purgatorio
    Purgatorio is the second canticle of Dante Alighieri’s Divine Comedy, depicting the poet’s ascent of Mount Purgatory as souls undergo purification on their way to Paradise.
  • D. Inferno
    Inferno is a distributed operating system developed at Bell Labs, known for its use of the Limbo programming language and its focus on portable, networked computing.
  • E. Inferno
    "Inferno" is a 1980s action thriller film best known for its desert survival and revenge storyline, directed by John G. Avildsen.
  • 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_69bd43f14cac819081c7c69803648211 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd650ad0f88190844bfcb46b3071c2 completed March 20, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be67c17eac8190bde930228a0f599a completed March 21, 2026, 9:41 a.m.
Created at: March 20, 2026, 1:20 p.m.