Triple

T992033
Position Surface form Disambiguated ID Type / Status
Subject Hanuman E21412 entity
Predicate epithet P743 FINISHED
Object Maruti
Maruti is another name for the Hindu deity Hanuman, revered as a symbol of strength, devotion, and protection.
 E117374 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: Maruti | Statement: [Hanuman, epithet, Maruti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Maruti
Context triple: [Hanuman, epithet, Maruti]
  • A. Tata
    Tata is a small town and oasis in southern Morocco, known as a gateway to the Anti-Atlas mountains and the surrounding desert landscapes.
  • B. Isuzu
    Isuzu is a Japanese automotive manufacturer best known for producing commercial vehicles, pickup trucks, and diesel engines for global markets.
  • C. Daihatsu Motor Co., Ltd.
    Daihatsu Motor Co., Ltd. is a Japanese automobile manufacturer best known for producing compact cars and kei vehicles, and operates as a subsidiary within the Toyota group.
  • D. Mobil
    Mobil is a major American oil company and fuel brand that became part of ExxonMobil after a 1999 merger.
  • E. Mazda Motor Corporation
    Mazda Motor Corporation is a Japanese automaker known for its innovative engineering, including rotary engines and driver-focused vehicles, and for its global presence in the automotive market.
  • 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: Maruti
Triple: [Hanuman, epithet, Maruti]
Generated description
Maruti is another name for the Hindu deity Hanuman, revered as a symbol of strength, devotion, and protection.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Maruti
Target entity description: Maruti is another name for the Hindu deity Hanuman, revered as a symbol of strength, devotion, and protection.
  • A. Tata
    Tata is a small town and oasis in southern Morocco, known as a gateway to the Anti-Atlas mountains and the surrounding desert landscapes.
  • B. Isuzu
    Isuzu is a Japanese automotive manufacturer best known for producing commercial vehicles, pickup trucks, and diesel engines for global markets.
  • C. Daihatsu Motor Co., Ltd.
    Daihatsu Motor Co., Ltd. is a Japanese automobile manufacturer best known for producing compact cars and kei vehicles, and operates as a subsidiary within the Toyota group.
  • D. Mobil
    Mobil is a major American oil company and fuel brand that became part of ExxonMobil after a 1999 merger.
  • E. Mazda Motor Corporation
    Mazda Motor Corporation is a Japanese automaker known for its innovative engineering, including rotary engines and driver-focused vehicles, and for its global presence in the automotive market.
  • 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_69a493c476b48190b41fc5e793171cc6 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b4c25e5081909ff1ada6b8bf617a completed March 1, 2026, 9:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac258f823c8190afeff79b6a4df911 completed March 7, 2026, 1:18 p.m.
NEDg Description generation batch_69ac261af46c81908d61b29ea97c0884 completed March 7, 2026, 1:20 p.m.
NED2 Entity disambiguation (via description) batch_69ac26ee09f0819098a7b1adcbb79053 completed March 7, 2026, 1:23 p.m.
Created at: March 1, 2026, 7:41 p.m.