Triple

T6620010
Position Surface form Disambiguated ID Type / Status
Subject Tapti River E149648 entity
Predicate passesNear P416 FINISHED
Object Multai
Multai is a town in Madhya Pradesh, India, known as a traditional source region of the Tapti River and a local religious and commercial center.
E601131 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: Multai | Statement: [Tapti River, passesNear, Multai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Multai
Context triple: [Tapti River, passesNear, Multai]
  • A. Mandulis
    Mandulis is a Nubian sun god venerated in the region of Lower Nubia, particularly during the Greco-Roman period.
  • B. Tahkuna
    Tahkuna is a coastal settlement in northern Estonia, located on Hiiumaa Island and known for its proximity to the historic Tahkuna Lighthouse.
  • C. Molėtai
    Molėtai is a small town in northeastern Lithuania known for its surrounding lakes, observatory, and role as a regional tourist and recreational center.
  • D. Kaikesi
    Kaikesi is a figure in the Hindu epic Ramayana, known as the rakshasi queen of Lanka and the mother of Ravana, Kumbhakarna, and Vibhishana.
  • E. Maitlis
    Maitlis is the surname of Emily Maitlis, a prominent British journalist and former lead presenter of BBC Two’s flagship news program Newsnight.
  • 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: Multai
Triple: [Tapti River, passesNear, Multai]
Generated description
Multai is a town in Madhya Pradesh, India, known as a traditional source region of the Tapti River and a local religious and commercial center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Multai
Target entity description: Multai is a town in Madhya Pradesh, India, known as a traditional source region of the Tapti River and a local religious and commercial center.
  • A. Mandulis
    Mandulis is a Nubian sun god venerated in the region of Lower Nubia, particularly during the Greco-Roman period.
  • B. Tahkuna
    Tahkuna is a coastal settlement in northern Estonia, located on Hiiumaa Island and known for its proximity to the historic Tahkuna Lighthouse.
  • C. Molėtai
    Molėtai is a small town in northeastern Lithuania known for its surrounding lakes, observatory, and role as a regional tourist and recreational center.
  • D. Kaikesi
    Kaikesi is a figure in the Hindu epic Ramayana, known as the rakshasi queen of Lanka and the mother of Ravana, Kumbhakarna, and Vibhishana.
  • E. Maitlis
    Maitlis is the surname of Emily Maitlis, a prominent British journalist and former lead presenter of BBC Two’s flagship news program Newsnight.
  • 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_69c687ed8a9c81908bb671717cb192ef completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6af7aff44819089da6145e1ef5f76 completed March 27, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cbde37288190b1e65589aa09b676 completed March 27, 2026, 6:26 p.m.
NEDg Description generation batch_69c6cd89b51c81909ea17d391732630e completed March 27, 2026, 6:33 p.m.
NED2 Entity disambiguation (via description) batch_69c6ce70442c8190a12a6c6eb76c5269 completed March 27, 2026, 6:37 p.m.
Created at: March 27, 2026, 1:58 p.m.