Triple

T3973632
Position Surface form Disambiguated ID Type / Status
Subject Avesta E85589 entity
Predicate hasPart P35 FINISHED
Object Visperad
Visperad is a Zoroastrian liturgical text and ceremony that expands upon the Yasna ritual with additional invocations to various divine beings.
 E403505 NE FINISHED

How this triple was built (4 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: Visperad | Statement: [Avesta, hasPart, Visperad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Visperad
Context triple: [Avesta, hasPart, Visperad]
  • A. Norvos
    Norvos is a theocratic, heavily fortified Free City in northern Essos known for its bearded priesthood and strict, austere culture.
  • B. Versonnex
    Versonnex is a small commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
  • C. Fensalir
    Fensalir is the misty, marsh-surrounded hall in Norse mythology that serves as the home of the goddess Frigg.
  • D. Novafora
    Novafora was a semiconductor company known for acquiring Transmeta to expand its presence in low-power microprocessor and video processing technologies.
  • E. Fremulon
    Fremulon is a television production company founded by Michael Schur, best known for producing acclaimed comedy series such as Brooklyn Nine-Nine.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Visperad
Triple: [Avesta, hasPart, Visperad]
Generated description
Visperad is a Zoroastrian liturgical text and ceremony that expands upon the Yasna ritual with additional invocations to various divine beings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Visperad
Target entity description: Visperad is a Zoroastrian liturgical text and ceremony that expands upon the Yasna ritual with additional invocations to various divine beings.
  • A. Norvos
    Norvos is a theocratic, heavily fortified Free City in northern Essos known for its bearded priesthood and strict, austere culture.
  • B. Versonnex
    Versonnex is a small commune in the Ain department of eastern France, located near the Swiss border in the Pays de Gex region.
  • C. Fensalir
    Fensalir is the misty, marsh-surrounded hall in Norse mythology that serves as the home of the goddess Frigg.
  • D. Novafora
    Novafora was a semiconductor company known for acquiring Transmeta to expand its presence in low-power microprocessor and video processing technologies.
  • E. Fremulon
    Fremulon is a television production company founded by Michael Schur, best known for producing acclaimed comedy series such as Brooklyn Nine-Nine.
  • F. None of above. chosen

Provenance (5 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_69aed93908348190a26c8aaf4fab3e86 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef99837cc8190b8b2464707f5e334 completed March 9, 2026, 4:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b540139c2c819080aa19b13540c76a completed March 14, 2026, 11:01 a.m.
NEDg Description generation batch_69b540ec36a4819082a9cbefc99bd683 completed March 14, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_69b5416d182c81908b1ae43ed097d288 completed March 14, 2026, 11:07 a.m.
Created at: March 9, 2026, 3:32 p.m.