Triple

T16527884
Position Surface form Disambiguated ID Type / Status
Subject Kumar Shahani E401486 entity
Predicate notableWork P4 FINISHED
Object Kasba
Kasba is an Indian art-house film directed by Kumar Shahani, known for its experimental narrative style and exploration of social and psychological themes.
E1218715 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: Kasba | Statement: [Kumar Shahani, notableWork, Kasba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kasba
Context triple: [Kumar Shahani, notableWork, Kasba]
  • A. Kasba
    Kasba is a town in the Purnia district of Bihar, India, known as a local commercial and administrative center for surrounding rural areas.
  • B. Al-Kahla
    Al-Kahla is a town located in southeastern Iraq within the Maysan Governorate, known for its proximity to the Mesopotamian marshlands and the Iran–Iraq border.
  • C. Kabra
    Kabra is a small rural locality in Central Queensland, Australia, situated near the town of Gracemere and the regional city of Rockhampton.
  • D. Qasar
    Qasar was a prominent member of the Mongol Borjigin clan, known historically as a close kinsman and military supporter of Genghis Khan.
  • E. Al-Qasr
    Al-Qasr is a town in Jordan notable for its location within the historically and archaeologically rich Karak 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: Kasba
Triple: [Kumar Shahani, notableWork, Kasba]
Generated description
Kasba is an Indian art-house film directed by Kumar Shahani, known for its experimental narrative style and exploration of social and psychological themes.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kasba
Target entity description: Kasba is an Indian art-house film directed by Kumar Shahani, known for its experimental narrative style and exploration of social and psychological themes.
  • A. Kasba
    Kasba is a town in the Purnia district of Bihar, India, known as a local commercial and administrative center for surrounding rural areas.
  • B. Al-Kahla
    Al-Kahla is a town located in southeastern Iraq within the Maysan Governorate, known for its proximity to the Mesopotamian marshlands and the Iran–Iraq border.
  • C. Kabra
    Kabra is a small rural locality in Central Queensland, Australia, situated near the town of Gracemere and the regional city of Rockhampton.
  • D. Qasar
    Qasar was a prominent member of the Mongol Borjigin clan, known historically as a close kinsman and military supporter of Genghis Khan.
  • E. Al-Qasr
    Al-Qasr is a town in Jordan notable for its location within the historically and archaeologically rich Karak 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_69d883838abc8190bc79cb2d41733ce2 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e32ed57be481908625d4c5aab0940c completed April 18, 2026, 7:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a00608efd0c81908e64419bd74eb285 completed May 10, 2026, 10:40 a.m.
NEDg Description generation batch_6a0062cbe9048190823db47a42dac26a completed May 10, 2026, 10:49 a.m.
NED2 Entity disambiguation (via description) batch_6a00635f57c08190ad915082b00b0f88 completed May 10, 2026, 10:52 a.m.
Created at: April 10, 2026, 5:14 a.m.