Triple

T9427989
Position Surface form Disambiguated ID Type / Status
Subject Vespertine E227302 entity
Predicate notableSingle P3283 FINISHED
Object Pagan Poetry E800012 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: Pagan Poetry | Statement: [Vespertine, notableSingle, Pagan Poetry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pagan Poetry
Context triple: [Vespertine, notableSingle, Pagan Poetry]
  • A. Pagan Poetry chosen
    "Pagan Poetry" is an experimental, emotionally intense art-pop song by Icelandic musician Björk from her 2001 album Vespertine.
  • B. The Pagan
    The Pagan is a 1929 silent romantic drama film starring Ramon Novarro, known for its South Seas setting and themes of cultural conflict and forbidden love.
  • C. Carmina (poems)
    Carmina is a collection of Latin poems by Theodulf of Orléans, reflecting the intellectual and religious culture of the Carolingian Renaissance.
  • D. Poésies sacrées
    Poésies sacrées is a collection of religious and devotional poems by the French poet Jean-Baptiste Rousseau, reflecting his turn toward spiritual themes.
  • E. Pagan
    Pagan, also known as Bagan, is an ancient city in Myanmar renowned for its vast plain of thousands of Buddhist temples and pagodas dating from the 9th to 13th centuries.
  • 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_69ca8436ba308190903e470776d2d893 completed March 30, 2026, 2:09 p.m.
NER Named-entity recognition batch_69cd7c92ee848190baa41fe91a131305 completed April 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1223d3cd8819089fec4c895125049 completed April 4, 2026, 2:37 p.m.
Created at: March 30, 2026, 7:49 p.m.