Triple

T11792417
Position Surface form Disambiguated ID Type / Status
Subject Pankaj Kapur E280419 entity
Predicate notableWork P4 FINISHED
Object Sehar
Sehar is a 2005 Indian crime drama film acclaimed for its realistic portrayal of the Uttar Pradesh police force and the criminal underworld.
E946894 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: Sehar | Statement: [Pankaj Kapur, notableWork, Sehar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sehar
Context triple: [Pankaj Kapur, notableWork, Sehar]
  • A. Barshaini
    Barshaini is a small Himalayan village in Himachal Pradesh, India, that serves as a popular base and trailhead for treks into the Parvati Valley and surrounding high-altitude landscapes.
  • B. Shabara
    Shabara was an early Indian philosopher and commentator best known for his influential exegesis on the Purva Mimamsa school of Hindu philosophy.
  • C. Sharya
    Sharya is a town in Kostroma Oblast, Russia, known as a regional railway junction and logging center.
  • D. Shimsha
    Shimsha is a river in southern India that flows through Karnataka and is known for its waterfalls and contribution to the Kaveri river system.
  • E. Shalim
    Shalim is a deity from ancient Canaanite religion, commonly associated with dusk or the setting sun.
  • 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: Sehar
Triple: [Pankaj Kapur, notableWork, Sehar]
Generated description
Sehar is a 2005 Indian crime drama film acclaimed for its realistic portrayal of the Uttar Pradesh police force and the criminal underworld.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sehar
Target entity description: Sehar is a 2005 Indian crime drama film acclaimed for its realistic portrayal of the Uttar Pradesh police force and the criminal underworld.
  • A. Barshaini
    Barshaini is a small Himalayan village in Himachal Pradesh, India, that serves as a popular base and trailhead for treks into the Parvati Valley and surrounding high-altitude landscapes.
  • B. Shabara
    Shabara was an early Indian philosopher and commentator best known for his influential exegesis on the Purva Mimamsa school of Hindu philosophy.
  • C. Sharya
    Sharya is a town in Kostroma Oblast, Russia, known as a regional railway junction and logging center.
  • D. Shimsha
    Shimsha is a river in southern India that flows through Karnataka and is known for its waterfalls and contribution to the Kaveri river system.
  • E. Shalim
    Shalim is a deity from ancient Canaanite religion, commonly associated with dusk or the setting sun.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a588d2c881909783c2d678c2a474 completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f09107fd2481908d765d2188035012 completed April 28, 2026, 10:50 a.m.
NEDg Description generation batch_69f0bd40108c8190863a60cf01cc7201 completed April 28, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69f0ef7e9f388190b33f6c16abadfde9 completed April 28, 2026, 5:33 p.m.
Created at: April 8, 2026, 9:42 p.m.