Triple

T7640218
Position Surface form Disambiguated ID Type / Status
Subject Varendra Research Museum E172980 entity
Predicate notableCollectionFrom P77477 FINISHED
Object Mainamati
Mainamati is an important archaeological site in Bangladesh known for its extensive Buddhist ruins and ancient monasteries dating from the 7th–12th centuries.
E677822 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: Mainamati | Statement: [Varendra Research Museum, notableCollectionFrom, Mainamati]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mainamati
Context triple: [Varendra Research Museum, notableCollectionFrom, Mainamati]
  • A. Kasarani
    Kasarani is a residential and commercial suburb in northeastern Nairobi, Kenya, known for hosting major sports and educational facilities.
  • B. Benipur
    Benipur is a town in the Darbhanga region of the Indian state of Bihar, known as a local center of trade and daily commerce.
  • C. Rogdai
    Rogdai is a fierce warrior antagonist from Alexander Pushkin’s narrative poem "Ruslan and Ludmila."
  • D. Kadamtala
    Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • E. Tathra
    Tathra is a coastal town on the Sapphire Coast of New South Wales, Australia, known for its historic wharf, scenic beaches, and fishing.
  • 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: Mainamati
Triple: [Varendra Research Museum, notableCollectionFrom, Mainamati]
Generated description
Mainamati is an important archaeological site in Bangladesh known for its extensive Buddhist ruins and ancient monasteries dating from the 7th–12th centuries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mainamati
Target entity description: Mainamati is an important archaeological site in Bangladesh known for its extensive Buddhist ruins and ancient monasteries dating from the 7th–12th centuries.
  • A. Kasarani
    Kasarani is a residential and commercial suburb in northeastern Nairobi, Kenya, known for hosting major sports and educational facilities.
  • B. Benipur
    Benipur is a town in the Darbhanga region of the Indian state of Bihar, known as a local center of trade and daily commerce.
  • C. Rogdai
    Rogdai is a fierce warrior antagonist from Alexander Pushkin’s narrative poem "Ruslan and Ludmila."
  • D. Kadamtala
    Kadamtala is a small settlement located on Middle Andaman Island in the Andaman and Nicobar Islands of India.
  • E. Tathra
    Tathra is a coastal town on the Sapphire Coast of New South Wales, Australia, known for its historic wharf, scenic beaches, and fishing.
  • 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_69c6995360188190968ee57b72a1627f completed March 27, 2026, 2:50 p.m.
NER Named-entity recognition batch_69c701731a288190b53ffc546a2f47d7 completed March 27, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69c870cd11648190b9aeedadb7bc1981 completed March 29, 2026, 12:22 a.m.
NEDg Description generation batch_69c872a531e08190b7488f576dcd7de4 completed March 29, 2026, 12:30 a.m.
NED2 Entity disambiguation (via description) batch_69c873846a188190a3a1cc56ac247fb0 completed March 29, 2026, 12:34 a.m.
Created at: March 27, 2026, 3:57 p.m.