Triple

T4512007
Position Surface form Disambiguated ID Type / Status
Subject Agni E102074 entity
Predicate epithet P743 FINISHED
Object Vahni
Vahni is a Sanskrit epithet of the Vedic fire god Agni, emphasizing his blazing, consuming aspect as sacred fire.
E448842 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: Vahni | Statement: [Agni, epithet, Vahni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vahni
Context triple: [Agni, epithet, Vahni]
  • A. Velda
    Velda is the loyal and resourceful secretary and love interest of private investigator Mike Hammer in the hardboiled crime novel and film "Kiss Me Deadly."
  • B. Vanth
    Vanth is the small, likely captured moon of the distant Kuiper Belt dwarf planet Orcus.
  • C. Tarana
    Tarana is the first name of Tarana Burke, the American civil rights activist who founded the Me Too movement.
  • D. Vestinian
    The Vestinians were an ancient Italic people of central Italy, culturally and linguistically related to other Sabellian tribes.
  • E. Vuvalini
    The Vuvalini are a matriarchal tribe of seasoned warrior women and survivalists in the Mad Max: Fury Road universe, known for their resilience and combat prowess in the post-apocalyptic wasteland.
  • 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: Vahni
Triple: [Agni, epithet, Vahni]
Generated description
Vahni is a Sanskrit epithet of the Vedic fire god Agni, emphasizing his blazing, consuming aspect as sacred fire.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Vahni
Target entity description: Vahni is a Sanskrit epithet of the Vedic fire god Agni, emphasizing his blazing, consuming aspect as sacred fire.
  • A. Velda
    Velda is the loyal and resourceful secretary and love interest of private investigator Mike Hammer in the hardboiled crime novel and film "Kiss Me Deadly."
  • B. Vanth
    Vanth is the small, likely captured moon of the distant Kuiper Belt dwarf planet Orcus.
  • C. Tarana
    Tarana is the first name of Tarana Burke, the American civil rights activist who founded the Me Too movement.
  • D. Vestinian
    The Vestinians were an ancient Italic people of central Italy, culturally and linguistically related to other Sabellian tribes.
  • E. Vuvalini
    The Vuvalini are a matriarchal tribe of seasoned warrior women and survivalists in the Mad Max: Fury Road universe, known for their resilience and combat prowess in the post-apocalyptic wasteland.
  • 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_69bd43d6251c81909deecce3e6e9d69c completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd571412788190a374abd1e05519e4 completed March 20, 2026, 2:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69bd7f875c4c81909e67d44b605816c2 completed March 20, 2026, 5:10 p.m.
NEDg Description generation batch_69bd802c09108190a21b2235710a0f74 completed March 20, 2026, 5:13 p.m.
NED2 Entity disambiguation (via description) batch_69bd84c11d8881908819b36669dee7b5 completed March 20, 2026, 5:32 p.m.
Created at: March 20, 2026, 1:01 p.m.