Triple

T13862211
Position Surface form Disambiguated ID Type / Status
Subject Dal Lake E333224 entity
Predicate hasIsland P970 FINISHED
Object Sona Lank
Sona Lank is a small island located within Dal Lake in Srinagar, Jammu and Kashmir, India.
E1066777 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: Sona Lank | Statement: [Dal Lake, hasIsland, Sona Lank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sona Lank
Context triple: [Dal Lake, hasIsland, Sona Lank]
  • A. Menik Vehera
    Menik Vehera is a ruined Buddhist monastery complex in the ancient Sri Lankan city of Polonnaruwa, notable for its brick stupa and surrounding monastic structures.
  • B. Sojitra
    Sojitra is a town in the Anand district of Gujarat, India, known for its agricultural surroundings and local dairy-based economy.
  • C. Sihala
    Sihala is a settlement in Pakistan located near the Soan River, known primarily for its proximity to this important waterway in the region.
  • D. Udaya
    Udaya is a given name most notably associated with D. Udaya Kumar, the Indian designer who created the Indian rupee sign.
  • E. Chanda
    Chanda was a historical kingdom associated with the Gond people, an indigenous community of central India.
  • 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: Sona Lank
Triple: [Dal Lake, hasIsland, Sona Lank]
Generated description
Sona Lank is a small island located within Dal Lake in Srinagar, Jammu and Kashmir, India.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sona Lank
Target entity description: Sona Lank is a small island located within Dal Lake in Srinagar, Jammu and Kashmir, India.
  • A. Menik Vehera
    Menik Vehera is a ruined Buddhist monastery complex in the ancient Sri Lankan city of Polonnaruwa, notable for its brick stupa and surrounding monastic structures.
  • B. Sojitra
    Sojitra is a town in the Anand district of Gujarat, India, known for its agricultural surroundings and local dairy-based economy.
  • C. Sihala
    Sihala is a settlement in Pakistan located near the Soan River, known primarily for its proximity to this important waterway in the region.
  • D. Udaya
    Udaya is a given name most notably associated with D. Udaya Kumar, the Indian designer who created the Indian rupee sign.
  • E. Chanda
    Chanda was a historical kingdom associated with the Gond people, an indigenous community of central India.
  • 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_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c20db88190acb842748aa01039 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c0ff1f78819088ae58f703e2c9ff completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c33437e8819085b6f79402500ba3 completed May 3, 2026, 9:50 p.m.
NED2 Entity disambiguation (via description) batch_69f7c3cd3cf0819099cc6cbd04c62e83 completed May 3, 2026, 9:53 p.m.
Created at: April 9, 2026, 10:14 p.m.