Triple

T4512126
Position Surface form Disambiguated ID Type / Status
Subject Varuṇa E102076 entity
Predicate symbol P129 FINISHED
Object makara
Makara is a mythical sea creature in Hindu and Buddhist traditions, often depicted as a composite aquatic beast and used as a vehicle or emblem of water deities.
 E448849 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: makara | Statement: [Varuṇa, symbol, makara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: makara
Context triple: [Varuṇa, symbol, makara]
  • A. Makatsch
    Makatsch is the surname of German actress and television presenter Heike Makatsch, known for her roles in films such as "Love Actually" and "Resident Evil."
  • B. Carakan
    Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
  • C. Karo
    Karo is a Jewish family name most famously associated with Rabbi Yosef Karo, the 16th-century author of the Shulchan Aruch.
  • D. Karo
    Karo are an indigenous Batak ethnic group of the highlands of North Sumatra, Indonesia, known for their distinct language, culture, and traditional village architecture.
  • E. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • 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: makara
Triple: [Varuṇa, symbol, makara]
Generated description
Makara is a mythical sea creature in Hindu and Buddhist traditions, often depicted as a composite aquatic beast and used as a vehicle or emblem of water deities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: makara
Target entity description: Makara is a mythical sea creature in Hindu and Buddhist traditions, often depicted as a composite aquatic beast and used as a vehicle or emblem of water deities.
  • A. Makatsch
    Makatsch is the surname of German actress and television presenter Heike Makatsch, known for her roles in films such as "Love Actually" and "Resident Evil."
  • B. Carakan
    Carakan is the traditional Javanese writing system used for the Javanese language and related regional languages of Indonesia.
  • C. Karo
    Karo is a Jewish family name most famously associated with Rabbi Yosef Karo, the 16th-century author of the Shulchan Aruch.
  • D. Karo
    Karo are an indigenous Batak ethnic group of the highlands of North Sumatra, Indonesia, known for their distinct language, culture, and traditional village architecture.
  • E. Tigak
    Tigak is an Austronesian language of the Meso-Melanesian subgroup spoken primarily in parts of Papua New Guinea.
  • 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.