Triple

T4986829
Position Surface form Disambiguated ID Type / Status
Subject Braj region E112023 entity
Predicate containsCity P294 FINISHED
Object Deeg
Deeg is a historic town in India’s Braj region, known for its 18th-century palace complex, gardens, and scenic water tanks built by the Jat rulers.
E485170 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: Deeg | Statement: [Braj region, containsCity, Deeg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Deeg
Context triple: [Braj region, containsCity, Deeg]
  • A. Mandsaur
    Mandsaur is a prominent city in northwestern Madhya Pradesh, India, known for its historical significance and agricultural and industrial economy.
  • B. Nestelghat
    Nestelghat was the nickname (bent-name) used by the Dutch Golden Age painter Leonaert Bramer within the Bentvueghels artists’ society in Rome.
  • C. Kawardha
    Kawardha is a regional dialect of the Chhattisgarhi language spoken in parts of the Indian state of Chhattisgarh.
  • D. Badami
    Badami is a historic town in Karnataka, India, renowned for its rock-cut cave temples and ancient Chalukyan architecture.
  • E. Thanesar
    Thanesar is a historic town in the Indian state of Haryana, renowned as an ancient center of learning and a significant site in Hindu mythology and the Mahabharata.
  • 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: Deeg
Triple: [Braj region, containsCity, Deeg]
Generated description
Deeg is a historic town in India’s Braj region, known for its 18th-century palace complex, gardens, and scenic water tanks built by the Jat rulers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Deeg
Target entity description: Deeg is a historic town in India’s Braj region, known for its 18th-century palace complex, gardens, and scenic water tanks built by the Jat rulers.
  • A. Mandsaur
    Mandsaur is a prominent city in northwestern Madhya Pradesh, India, known for its historical significance and agricultural and industrial economy.
  • B. Nestelghat
    Nestelghat was the nickname (bent-name) used by the Dutch Golden Age painter Leonaert Bramer within the Bentvueghels artists’ society in Rome.
  • C. Kawardha
    Kawardha is a regional dialect of the Chhattisgarhi language spoken in parts of the Indian state of Chhattisgarh.
  • D. Badami
    Badami is a historic town in Karnataka, India, renowned for its rock-cut cave temples and ancient Chalukyan architecture.
  • E. Thanesar
    Thanesar is a historic town in the Indian state of Haryana, renowned as an ancient center of learning and a significant site in Hindu mythology and the Mahabharata.
  • 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_69bd441be7bc8190b530362d427b97d2 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd727c25bc8190b72f6ddd3772c80a completed March 20, 2026, 4:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a1ca3ec81908ad750cd9e899bcc completed March 21, 2026, 12:07 p.m.
NEDg Description generation batch_69be8a7e90b08190852cc45b7d8f0dc7 completed March 21, 2026, 12:09 p.m.
NED2 Entity disambiguation (via description) batch_69be8b4411b48190a12d694321453492 completed March 21, 2026, 12:12 p.m.
Created at: March 20, 2026, 1:34 p.m.