Triple

T18399151
Position Surface form Disambiguated ID Type / Status
Subject Vedic prosody E449944 entity
Predicate classifies P34022 FINISHED
Object Pankti metre
Pankti metre is a Vedic poetic meter characterized by verses of five equal-length lines used in ancient Sanskrit hymns.
E1322101 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: Pankti metre | Statement: [Vedic prosody, classifies, Pankti metre]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pankti metre
Context triple: [Vedic prosody, classifies, Pankti metre]
  • A. Meteren
    Meteren is a village in the Dutch province of Gelderland, located within the municipality of West Betuwe.
  • B. Panenka
    Panenka is a famous football penalty-taking technique in which the kicker delicately chips the ball down the center of the goal, typically as the goalkeeper dives to one side.
  • C. Pantjeny
    Pantjeny was a relatively obscure pharaoh of ancient Egypt’s 13th Dynasty, ruling during the politically fragmented Second Intermediate Period.
  • D. Paite
    Paite are an indigenous ethnic community of the broader Mizo group, primarily inhabiting parts of Northeast India and Myanmar, with their own distinct language and cultural traditions.
  • E. Mētriena
    Mētriena is a village and administrative unit in eastern Latvia, located within Madona Municipality.
  • 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: Pankti metre
Triple: [Vedic prosody, classifies, Pankti metre]
Generated description
Pankti metre is a Vedic poetic meter characterized by verses of five equal-length lines used in ancient Sanskrit hymns.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pankti metre
Target entity description: Pankti metre is a Vedic poetic meter characterized by verses of five equal-length lines used in ancient Sanskrit hymns.
  • A. Meteren
    Meteren is a village in the Dutch province of Gelderland, located within the municipality of West Betuwe.
  • B. Panenka
    Panenka is a famous football penalty-taking technique in which the kicker delicately chips the ball down the center of the goal, typically as the goalkeeper dives to one side.
  • C. Pantjeny
    Pantjeny was a relatively obscure pharaoh of ancient Egypt’s 13th Dynasty, ruling during the politically fragmented Second Intermediate Period.
  • D. Paite
    Paite are an indigenous ethnic community of the broader Mizo group, primarily inhabiting parts of Northeast India and Myanmar, with their own distinct language and cultural traditions.
  • E. Mētriena
    Mētriena is a village and administrative unit in eastern Latvia, located within Madona Municipality.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e518499b1481909c5de786c48faeba completed April 19, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e2427c448190b3562d7cb0313d5a completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e2ca62f881908122f2d2fe3b937d completed May 13, 2026, 2:32 a.m.
NED2 Entity disambiguation (via description) batch_6a03e33718f481909377eeff33332f33 completed May 13, 2026, 2:34 a.m.
Created at: April 10, 2026, 10:46 a.m.