Triple

T3961250
Position Surface form Disambiguated ID Type / Status
Subject Sinhagad Fort E85907 entity
Predicate previousName P65 FINISHED
Object Kondhana
Kondhana is the historic hill fortress near Pune, India, later known as Sinhagad, renowned for its strategic importance and role in Maratha history.
 E401507 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: Kondhana | Statement: [Sinhagad Fort, previousName, Kondhana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kondhana
Context triple: [Sinhagad Fort, previousName, Kondhana]
  • A. Kundagannada
    Kundagannada is a regional dialect of the Kannada language spoken primarily in the coastal districts of Karnataka, India.
  • B. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of Papua New Guinea.
  • C. Manikonda
    Manikonda is a rapidly developing residential and IT suburb in the western part of Hyderabad, known for its proximity to major technology hubs and corporate campuses.
  • D. Konda-Dora
    Konda-Dora is a South-Central Dravidian language spoken primarily by the Konda Dora tribal community in parts of Andhra Pradesh and Odisha, India.
  • E. Nok Kundi
    Nok Kundi is a small town in Pakistan’s Balochistan province, known as a remote settlement near the border with Iran and Afghanistan.
  • 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: Kondhana
Triple: [Sinhagad Fort, previousName, Kondhana]
Generated description
Kondhana is the historic hill fortress near Pune, India, later known as Sinhagad, renowned for its strategic importance and role in Maratha history.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kondhana
Target entity description: Kondhana is the historic hill fortress near Pune, India, later known as Sinhagad, renowned for its strategic importance and role in Maratha history.
  • A. Kundagannada
    Kundagannada is a regional dialect of the Kannada language spoken primarily in the coastal districts of Karnataka, India.
  • B. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of Papua New Guinea.
  • C. Manikonda
    Manikonda is a rapidly developing residential and IT suburb in the western part of Hyderabad, known for its proximity to major technology hubs and corporate campuses.
  • D. Konda-Dora
    Konda-Dora is a South-Central Dravidian language spoken primarily by the Konda Dora tribal community in parts of Andhra Pradesh and Odisha, India.
  • E. Nok Kundi
    Nok Kundi is a small town in Pakistan’s Balochistan province, known as a remote settlement near the border with Iran and Afghanistan.
  • 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_69aed93a96908190bcbdbfa718f155bd completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef9617adc8190874b97a612fa7c72 completed March 9, 2026, 4:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533b8e00c819093af24f27eee793b completed March 14, 2026, 10:08 a.m.
NEDg Description generation batch_69b5346fb3648190b2b72e10179588ed completed March 14, 2026, 10:11 a.m.
NED2 Entity disambiguation (via description) batch_69b534e98b8081909c2b71ff20fe0bb4 completed March 14, 2026, 10:14 a.m.
Created at: March 9, 2026, 3:31 p.m.