Triple

T2838476
Position Surface form Disambiguated ID Type / Status
Subject Malwa (Punjab) E62407 entity
Predicate includesCity P3207 FINISHED
Object Mansa
Mansa is a city in the Malwa region of Punjab, India, known primarily as an agricultural and cotton-growing center.
 E304503 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: Mansa | Statement: [Malwa (Punjab), includesCity, Mansa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mansa
Context triple: [Malwa (Punjab), includesCity, Mansa]
  • A. Ngoni
    Ngoni is a Bantu language spoken by the Ngoni people of parts of Malawi, Tanzania, Mozambique, and Zambia, reflecting historical migrations from the Zulu region.
  • B. Mandura Gumuz
    Mandura Gumuz is a Gumuz language spoken by the Gumuz people of western Ethiopia.
  • C. Musa
    Musa is a central character in Arundhati Roy’s novel "The Ministry of Utmost Happiness," around whom key political and personal conflicts in Kashmir revolve.
  • D. Musa
    Musa is the name used in the Quran for the prophet Moses, a central figure in Islamic tradition known for leading the Israelites and receiving divine revelation.
  • E. Idrissa
    Idrissa is the given first name of British actor, producer, and musician Idris Elba.
  • 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: Mansa
Triple: [Malwa (Punjab), includesCity, Mansa]
Generated description
Mansa is a city in the Malwa region of Punjab, India, known primarily as an agricultural and cotton-growing center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mansa
Target entity description: Mansa is a city in the Malwa region of Punjab, India, known primarily as an agricultural and cotton-growing center.
  • A. Ngoni
    Ngoni is a Bantu language spoken by the Ngoni people of parts of Malawi, Tanzania, Mozambique, and Zambia, reflecting historical migrations from the Zulu region.
  • B. Mandura Gumuz
    Mandura Gumuz is a Gumuz language spoken by the Gumuz people of western Ethiopia.
  • C. Musa
    Musa is a central character in Arundhati Roy’s novel "The Ministry of Utmost Happiness," around whom key political and personal conflicts in Kashmir revolve.
  • D. Musa
    Musa is the name used in the Quran for the prophet Moses, a central figure in Islamic tradition known for leading the Israelites and receiving divine revelation.
  • E. Idrissa
    Idrissa is the given first name of British actor, producer, and musician Idris Elba.
  • 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_69ab4c3d16bc81908b3a1c98fbd287fe completed March 6, 2026, 9:50 p.m.
NER Named-entity recognition batch_69abdef015bc81909f6a2ff17b22862f completed March 7, 2026, 8:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69afe8cbaa4081909ff4e9fdf590e352 completed March 10, 2026, 9:47 a.m.
NEDg Description generation batch_69afea1732b481909a8df01d80ca1bd4 completed March 10, 2026, 9:53 a.m.
NED2 Entity disambiguation (via description) batch_69b00eff94b481909a4cc08c8494870c completed March 10, 2026, 12:30 p.m.
Created at: March 6, 2026, 10:01 p.m.