Triple

T21844275
Position Surface form Disambiguated ID Type / Status
Subject Aži Dahāka E539334 entity
Predicate originatesInText P134241 FINISHED
Object Avesta NE NERFINISHED

How this triple was built (3 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: Avesta | Statement: [Aži Dahāka, originatesInText, Avesta]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Avesta
Context triple: [Aži Dahāka, originatesInText, Avesta]
  • A. Avesta chosen
    The Avesta is the primary collection of sacred scriptures of Zoroastrianism, containing hymns, liturgical texts, and religious teachings.
  • B. Avesta
    Avesta is a small industrial town in central Sweden known for its steel production heritage and location along the Dalälven River.
  • C. Shahnameh
    Shahnameh is an epic poem by Ferdowsi that recounts the mythological and historical past of Greater Iran and is considered one of the most important works of Persian literature.
  • D. Psalter Pahlavi
    Psalter Pahlavi is a historical variant of the Pahlavi script used primarily in a Middle Persian translation of the Psalms, notable for its distinctive letter forms and limited manuscript tradition.
  • E. Vedas
    The Vedas are a collection of ancient sacred texts composed in Sanskrit that form the foundational spiritual and philosophical scriptures of Hinduism.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: originatesInText
Context triple: [Aži Dahāka, originatesInText, Avesta]
  • A. locatedInTextualSource chosen
    Indicates that information about an entity or relation appears within, or is documented by, a specific textual source.
  • B. originatesAs
    Indicates that one entity begins, arises, or comes into existence in the form, state, or role specified by another entity.
  • C. originalText
    Indicates that one text is the initial, unmodified version from which other versions, translations, or representations are derived.
  • D. followsInText
    Indicates that one textual element appears immediately or subsequently after another within the same text.
  • E. originallyIn
    Indicates that something first appeared, was created, or was initially located within a particular context, source, or place.
  • 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_69e0c476c3c88190a92d08ebb59a128a completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69f0bd5248f08190ba208512eafbe7ad completed April 28, 2026, 1:59 p.m.
PD Predicate disambiguation batch_69e6be8c14748190bdcc44a14d50bea4 completed April 21, 2026, 12:02 a.m.
Created at: April 16, 2026, 6:55 p.m.