Triple

T14490889
Position Surface form Disambiguated ID Type / Status
Subject Amba E359358 entity
Predicate epithet P743 FINISHED
Object Ambe Maa
Ambe Maa is a revered Hindu goddess form of Amba, worshipped especially in western India as a powerful and protective mother deity.
E965768 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: Ambe Maa | Statement: [Amba, epithet, Ambe Maa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ambe Maa
Context triple: [Amba, epithet, Ambe Maa]
  • A. Kamakshi
    Kamakshi is a revered form of the Hindu goddess Parvati, worshipped especially in Kanchipuram as a central deity of Shakta tradition.
  • B. Jeen Mata
    Jeen Mata is a Hindu goddess venerated primarily in Rajasthan, India, where she is revered as a powerful local deity and protector.
  • C. Amma
    Amma is the popular honorific nickname of J. Jayalalithaa, the influential Indian politician and long-serving Chief Minister of Tamil Nadu.
  • D. Amma
    Amma is a fictional female protagonist, likely a central figure in a narrative focused on a girl or woman’s experiences.
  • E. Marudevi
    Marudevi is revered in Jain tradition as the mother of the first Tirthankara, Rishabhanatha, and an important figure in early Jain spiritual narratives.
  • 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: Ambe Maa
Triple: [Amba, epithet, Ambe Maa]
Generated description
Ambe Maa is a revered Hindu goddess form of Amba, worshipped especially in western India as a powerful and protective mother deity.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Ambe Maa
Target entity description: Ambe Maa is a revered Hindu goddess form of Amba, worshipped especially in western India as a powerful and protective mother deity.
  • A. Kamakshi
    Kamakshi is a revered form of the Hindu goddess Parvati, worshipped especially in Kanchipuram as a central deity of Shakta tradition.
  • B. Jeen Mata chosen
    Jeen Mata is a Hindu goddess venerated primarily in Rajasthan, India, where she is revered as a powerful local deity and protector.
  • C. Amma
    Amma is the popular honorific nickname of J. Jayalalithaa, the influential Indian politician and long-serving Chief Minister of Tamil Nadu.
  • D. Amma
    Amma is a fictional female protagonist, likely a central figure in a narrative focused on a girl or woman’s experiences.
  • E. Marudevi
    Marudevi is revered in Jain tradition as the mother of the first Tirthankara, Rishabhanatha, and an important figure in early Jain spiritual narratives.
  • F. None of above.

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_69d8279740308190af9df93a3af8592e completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de930d820481908b9813014dd02540 completed April 14, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd6d9334708190baa2f8094df3c09e completed May 8, 2026, 4:58 a.m.
NEDg Description generation batch_69fd6f80e3a081908c43915275898852 completed May 8, 2026, 5:07 a.m.
NED2 Entity disambiguation (via description) batch_69fd7016a3c48190a1ea2fefeea92c60 completed May 8, 2026, 5:09 a.m.
Created at: April 10, 2026, 1:20 a.m.