Triple

T5009086
Position Surface form Disambiguated ID Type / Status
Subject Tiresias E112569 entity
Predicate appearsInWork P795 FINISHED
Object Dante’s Inferno E105627 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: Dante’s Inferno | Statement: [Tiresias, appearsInWork, Dante’s Inferno]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dante’s Inferno
Context triple: [Tiresias, appearsInWork, Dante’s Inferno]
  • A. The Inferno
    The Inferno is the passionate and raucous student section that supports the Arizona State Sun Devils football team at their home games.
  • B. Divine Comedy
    The Divine Comedy is an epic Italian poem by Dante Alighieri that narrates a visionary journey through Hell, Purgatory, and Paradise and stands as one of the foundational works of Western literature.
  • C. Inferno chosen
    Inferno is the first cantica of Dante Alighieri’s Divine Comedy, depicting the poet’s allegorical journey through the nine circles of Hell.
  • D. Inferno
    Inferno is an autobiographical novel by August Strindberg that chronicles his psychological crisis, occult obsessions, and descent into paranoia during his years in Paris.
  • E. 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.
  • 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_69bd4433d0b08190877e83959ef40d81 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd72eb05f881908d7dc3d7cd07b2ae completed March 20, 2026, 4:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69bea473a1708190aaf4a021fec472c6 completed March 21, 2026, 2 p.m.
Created at: March 20, 2026, 1:35 p.m.