Triple

T10736696
Position Surface form Disambiguated ID Type / Status
Subject Kundapura taluk E253212 entity
Predicate hasVillage P4011 FINISHED
Object Gangolli
Gangolli is a coastal village in Karnataka, India, known for its fishing harbor and location near the confluence of multiple rivers with the Arabian Sea.
E883641 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: Gangolli | Statement: [Kundapura taluk, hasVillage, Gangolli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gangolli
Context triple: [Kundapura taluk, hasVillage, Gangolli]
  • A. Gangoli
    Gangoli is a regional dialect of the Kumaoni language spoken in parts of Uttarakhand in northern India.
  • B. Chholiya
    Chholiya is a traditional folk dance of the Kumaon region of Uttarakhand, India, often performed at weddings and festivals and characterized by its sword-and-shield martial style.
  • C. Banshiwala
    Banshiwala is a Bengali novel by acclaimed writer Shirshendu Mukhopadhyay, known for its evocative storytelling and exploration of human relationships.
  • D. Rao Bika
    Rao Bika was a 15th-century Rajput prince of the Rathore clan who established and ruled the kingdom that became the city of Bikaner in present-day Rajasthan, India.
  • E. Guddu
    Guddu is a town in Pakistan best known for its proximity to the Guddu Barrage on the Indus River.
  • 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: Gangolli
Triple: [Kundapura taluk, hasVillage, Gangolli]
Generated description
Gangolli is a coastal village in Karnataka, India, known for its fishing harbor and location near the confluence of multiple rivers with the Arabian Sea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Gangolli
Target entity description: Gangolli is a coastal village in Karnataka, India, known for its fishing harbor and location near the confluence of multiple rivers with the Arabian Sea.
  • A. Gangoli
    Gangoli is a regional dialect of the Kumaoni language spoken in parts of Uttarakhand in northern India.
  • B. Chholiya
    Chholiya is a traditional folk dance of the Kumaon region of Uttarakhand, India, often performed at weddings and festivals and characterized by its sword-and-shield martial style.
  • C. Banshiwala
    Banshiwala is a Bengali novel by acclaimed writer Shirshendu Mukhopadhyay, known for its evocative storytelling and exploration of human relationships.
  • D. Rao Bika
    Rao Bika was a 15th-century Rajput prince of the Rathore clan who established and ruled the kingdom that became the city of Bikaner in present-day Rajasthan, India.
  • E. Guddu
    Guddu is a town in Pakistan best known for its proximity to the Guddu Barrage on the Indus River.
  • 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_69d6aa5e51e8819095f06881cecf152e completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d71022aee0819091a5790d3dee6777 completed April 9, 2026, 2:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69de22cc4edc8190a7ab45e57ed94c47 completed April 14, 2026, 11:19 a.m.
NEDg Description generation batch_69de271ca4f081908d78a20b25ebd25c completed April 14, 2026, 11:38 a.m.
NED2 Entity disambiguation (via description) batch_69de2ccee0cc8190acd24d5c225f7cde completed April 14, 2026, 12:02 p.m.
Created at: April 8, 2026, 9:14 p.m.