Triple

T5010264
Position Surface form Disambiguated ID Type / Status
Subject Ravana E112600 entity
Predicate epithet P743 FINISHED
Object Lankeshwara
Lankeshwara is an epithet of Ravana, the legendary king of Lanka in the Hindu epic Ramayana, highlighting his role as the lord and ruler of the island kingdom.
 E486059 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: Lankeshwara | Statement: [Ravana, epithet, Lankeshwara]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lankeshwara
Context triple: [Ravana, epithet, Lankeshwara]
  • A. Sangameshwar
    Sangameshwar is a town in Maharashtra, India, historically notable as the site where Maratha ruler Sambhaji was captured by Mughal forces.
  • B. Mukteshwar
    Mukteshwar is a scenic hill town in Uttarakhand, India, known for its panoramic Himalayan views, fruit orchards, and tranquil forests.
  • C. Bageshwar
    Bageshwar is a town and district headquarters in the Kumaon region of Uttarakhand, India, known for its religious significance and scenic Himalayan surroundings.
  • D. Suvarnamukhi
    Suvarnamukhi is a river in southern India that serves as a tributary of the Arkavathi River, contributing to the regional drainage and water system.
  • E. Santeshivara
    Santeshivara is the given first name of the renowned Indian novelist and philosopher S. L. Bhyrappa.
  • 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: Lankeshwara
Triple: [Ravana, epithet, Lankeshwara]
Generated description
Lankeshwara is an epithet of Ravana, the legendary king of Lanka in the Hindu epic Ramayana, highlighting his role as the lord and ruler of the island kingdom.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lankeshwara
Target entity description: Lankeshwara is an epithet of Ravana, the legendary king of Lanka in the Hindu epic Ramayana, highlighting his role as the lord and ruler of the island kingdom.
  • A. Sangameshwar
    Sangameshwar is a town in Maharashtra, India, historically notable as the site where Maratha ruler Sambhaji was captured by Mughal forces.
  • B. Mukteshwar
    Mukteshwar is a scenic hill town in Uttarakhand, India, known for its panoramic Himalayan views, fruit orchards, and tranquil forests.
  • C. Bageshwar
    Bageshwar is a town and district headquarters in the Kumaon region of Uttarakhand, India, known for its religious significance and scenic Himalayan surroundings.
  • D. Suvarnamukhi
    Suvarnamukhi is a river in southern India that serves as a tributary of the Arkavathi River, contributing to the regional drainage and water system.
  • E. Santeshivara
    Santeshivara is the given first name of the renowned Indian novelist and philosopher S. L. Bhyrappa.
  • 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_69bd4434acb8819086679dbeccc2fe54 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd730bdb208190bebd7f22839ab6e5 completed March 20, 2026, 4:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69be9269e72881908ea49a77a83b8958 completed March 21, 2026, 12:43 p.m.
NEDg Description generation batch_69be933f3ed08190a128c1b3c9b3b1c3 completed March 21, 2026, 12:46 p.m.
NED2 Entity disambiguation (via description) batch_69be940b2eac819099001d403501afac completed March 21, 2026, 12:50 p.m.
Created at: March 20, 2026, 1:35 p.m.