Triple

T16155165
Position Surface form Disambiguated ID Type / Status
Subject Agra district E392020 entity
Predicate hasTown P847 FINISHED
Object Kiraoli
Kiraoli is a town in the Agra district of Uttar Pradesh, India, known for its location along major road and rail routes connecting Agra with nearby regions.
E1198036 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: Kiraoli | Statement: [Agra district, hasTown, Kiraoli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kiraoli
Context triple: [Agra district, hasTown, Kiraoli]
  • A. Karemeis
    Karemeis is the ancient or historical name of the town now known as Koropi in eastern Attica, Greece.
  • B. Rausu
    Rausu is a small coastal town on Japan’s Shiretoko Peninsula, known for its rich marine wildlife, drift ice sightseeing, and access to the remote natural landscapes of eastern Hokkaido.
  • C. Koidula
    Koidula is a railway junction and border station in southeastern Estonia that serves as a key transit point near the Russian and Latvian borders.
  • D. Kiebu
    Kiebu is the main settlement and administrative center of the island of Makin in Kiribati.
  • E. Makiivka
    Makiivka is a large industrial city in eastern Ukraine known for its coal mining and heavy industry, located near Donetsk in the Donbas region.
  • 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: Kiraoli
Triple: [Agra district, hasTown, Kiraoli]
Generated description
Kiraoli is a town in the Agra district of Uttar Pradesh, India, known for its location along major road and rail routes connecting Agra with nearby regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kiraoli
Target entity description: Kiraoli is a town in the Agra district of Uttar Pradesh, India, known for its location along major road and rail routes connecting Agra with nearby regions.
  • A. Karemeis
    Karemeis is the ancient or historical name of the town now known as Koropi in eastern Attica, Greece.
  • B. Rausu
    Rausu is a small coastal town on Japan’s Shiretoko Peninsula, known for its rich marine wildlife, drift ice sightseeing, and access to the remote natural landscapes of eastern Hokkaido.
  • C. Koidula
    Koidula is a railway junction and border station in southeastern Estonia that serves as a key transit point near the Russian and Latvian borders.
  • D. Kiebu
    Kiebu is the main settlement and administrative center of the island of Makin in Kiribati.
  • E. Makiivka
    Makiivka is a large industrial city in eastern Ukraine known for its coal mining and heavy industry, located near Donetsk in the Donbas region.
  • 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_69d87f1c65e48190aa2b4c472e9bafc4 completed April 10, 2026, 4:39 a.m.
NER Named-entity recognition batch_69e21e5902a08190ad8694955ef6073a completed April 17, 2026, 11:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69fff7ae46dc81908cba9152a6080c3a completed May 10, 2026, 3:12 a.m.
NEDg Description generation batch_69fff86a556c819096bc008e1ca76e8c completed May 10, 2026, 3:15 a.m.
NED2 Entity disambiguation (via description) batch_69fff926120081909f1042bf3a16ea10 completed May 10, 2026, 3:19 a.m.
Created at: April 10, 2026, 5:01 a.m.