Triple

T16608448
Position Surface form Disambiguated ID Type / Status
Subject Yasna E403504 entity
Predicate uses P98 FINISHED
Object Haoma
Haoma is a sacred plant and its deified spirit in Zoroastrianism, central to ritual offerings and associated with purification, vitality, and divine inspiration.
E1222719 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: Haoma | Statement: [Yasna, uses, Haoma]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haoma
Context triple: [Yasna, uses, Haoma]
  • A. Wormwood
    Wormwood is a 2017 Netflix docudrama miniseries by Errol Morris that blends documentary interviews with dramatized scenes to explore the mysterious death of scientist Frank Olson and the CIA’s MK-Ultra program.
  • B. Wormwood
    "Wormwood" is a crime novel by David Levien, known for its gritty, suspenseful storytelling and exploration of the darker sides of human nature.
  • C. Sahl Hasheesh
    Sahl Hasheesh is a modern Red Sea coastal resort town in Egypt known for its luxury hotels, beaches, and diving and snorkeling sites.
  • D. Qumis
    Qumis was an ancient historical region in north-central Iran, situated along key trade routes and adjacent to Tabaristan.
  • E. Homa
    Homa is the surname of American professional golfer Max Homa, a multiple-time PGA Tour winner.
  • 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: Haoma
Triple: [Yasna, uses, Haoma]
Generated description
Haoma is a sacred plant and its deified spirit in Zoroastrianism, central to ritual offerings and associated with purification, vitality, and divine inspiration.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haoma
Target entity description: Haoma is a sacred plant and its deified spirit in Zoroastrianism, central to ritual offerings and associated with purification, vitality, and divine inspiration.
  • A. Wormwood
    Wormwood is a 2017 Netflix docudrama miniseries by Errol Morris that blends documentary interviews with dramatized scenes to explore the mysterious death of scientist Frank Olson and the CIA’s MK-Ultra program.
  • B. Wormwood
    "Wormwood" is a crime novel by David Levien, known for its gritty, suspenseful storytelling and exploration of the darker sides of human nature.
  • C. Sahl Hasheesh
    Sahl Hasheesh is a modern Red Sea coastal resort town in Egypt known for its luxury hotels, beaches, and diving and snorkeling sites.
  • D. Qumis
    Qumis was an ancient historical region in north-central Iran, situated along key trade routes and adjacent to Tabaristan.
  • E. Homa
    Homa is the surname of American professional golfer Max Homa, a multiple-time PGA Tour winner.
  • 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_69d883880d0c81908b5fcd454e767b60 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e36093901881909b85af47f75879a9 completed April 18, 2026, 10:44 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0075aa79408190b395d4cd9c6c1cb7 completed May 10, 2026, 12:10 p.m.
NEDg Description generation batch_6a00768e9720819094d4e11ee1e100d6 completed May 10, 2026, 12:14 p.m.
NED2 Entity disambiguation (via description) batch_6a007728680c819082a3bd7e84edb2b0 completed May 10, 2026, 12:16 p.m.
Created at: April 10, 2026, 5:17 a.m.