Triple

T14972951
Position Surface form Disambiguated ID Type / Status
Subject Pamba River E373368 entity
Predicate tributary P415 FINISHED
Object Kakkiyar
Kakkiyar is a smaller river in the Indian state of Kerala that feeds into the Pamba River as one of its tributaries.
 E1129765 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: Kakkiyar | Statement: [Pamba River, tributary, Kakkiyar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kakkiyar
Context triple: [Pamba River, tributary, Kakkiyar]
  • A. Kadaru
    Kadaru is a Nubian language spoken by the Kadaru people in parts of Sudan.
  • B. Kuduru
    Kuduru is a community located within the Bwari Area Council in Nigeria’s Federal Capital Territory.
  • C. Chakia
    Chakia is a town in the East Champaran district of the Indian state of Bihar, known primarily as a local administrative and market center for the surrounding rural region.
  • D. Kumaoni
    Kumaoni is an Indo-Aryan language spoken primarily in the Kumaon region of India’s Uttarakhand state, known for its rich oral traditions and distinct dialects.
  • E. Kammala
    Kammala was a historical figure known primarily as one of the children of Zhenjin, the Crown Prince of the Yuan dynasty and son of Kublai Khan.
  • 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: Kakkiyar
Triple: [Pamba River, tributary, Kakkiyar]
Generated description
Kakkiyar is a smaller river in the Indian state of Kerala that feeds into the Pamba River as one of its tributaries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kakkiyar
Target entity description: Kakkiyar is a smaller river in the Indian state of Kerala that feeds into the Pamba River as one of its tributaries.
  • A. Kadaru
    Kadaru is a Nubian language spoken by the Kadaru people in parts of Sudan.
  • B. Kuduru
    Kuduru is a community located within the Bwari Area Council in Nigeria’s Federal Capital Territory.
  • C. Chakia
    Chakia is a town in the East Champaran district of the Indian state of Bihar, known primarily as a local administrative and market center for the surrounding rural region.
  • D. Kumaoni
    Kumaoni is an Indo-Aryan language spoken primarily in the Kumaon region of India’s Uttarakhand state, known for its rich oral traditions and distinct dialects.
  • E. Kammala
    Kammala was a historical figure known primarily as one of the children of Zhenjin, the Crown Prince of the Yuan dynasty and son of Kublai Khan.
  • 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_69d85ccbbcd48190acb56e7cf104d8ad completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded6e767608190940eb6f16ea97451 completed April 15, 2026, 12:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe8be8af688190832efb00695f8b20 completed May 9, 2026, 1:20 a.m.
NEDg Description generation batch_69fe8f39388c81909d6eb44f3433982e completed May 9, 2026, 1:34 a.m.
NED2 Entity disambiguation (via description) batch_69fe8fa960888190ab1fa4bcf426be4b completed May 9, 2026, 1:36 a.m.
Created at: April 10, 2026, 2:50 a.m.