Triple

T9794232
Position Surface form Disambiguated ID Type / Status
Subject Persis Khambatta E237677 entity
Predicate notableWork P4 FINISHED
Object Loha
Loha is a 1987 Indian Hindi-language action film featuring Persis Khambatta in a prominent role.
 E822241 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: Loha | Statement: [Persis Khambatta, notableWork, Loha]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Loha
Context triple: [Persis Khambatta, notableWork, Loha]
  • A. Ratna
    Ratna is an Indonesian-born dancer and model who became known internationally as the second wife of French photographer Henri Cartier-Bresson.
  • B. Aokaparangi
    Aokaparangi is a mountain peak in New Zealand’s Tararua Range, popular with trampers for its alpine terrain and expansive views.
  • C. Rohilla
    The Rohilla are a Pashtun-origin community historically known for establishing the Rohilkhand region in northern India and playing a significant role in 18th-century North Indian politics.
  • D. Kahaku
    Kahaku is Japan’s National Museum of Nature and Science in Tokyo, renowned for its extensive natural history and scientific collections and exhibitions.
  • E. Gohana
    Gohana is a town and municipal council in the Indian state of Haryana, known as a local commercial and agricultural hub in the Sonipat 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: Loha
Triple: [Persis Khambatta, notableWork, Loha]
Generated description
Loha is a 1987 Indian Hindi-language action film featuring Persis Khambatta in a prominent role.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Loha
Target entity description: Loha is a 1987 Indian Hindi-language action film featuring Persis Khambatta in a prominent role.
  • A. Ratna
    Ratna is an Indonesian-born dancer and model who became known internationally as the second wife of French photographer Henri Cartier-Bresson.
  • B. Aokaparangi
    Aokaparangi is a mountain peak in New Zealand’s Tararua Range, popular with trampers for its alpine terrain and expansive views.
  • C. Rohilla
    The Rohilla are a Pashtun-origin community historically known for establishing the Rohilkhand region in northern India and playing a significant role in 18th-century North Indian politics.
  • D. Kahaku
    Kahaku is Japan’s National Museum of Nature and Science in Tokyo, renowned for its extensive natural history and scientific collections and exhibitions.
  • E. Gohana
    Gohana is a town and municipal council in the Indian state of Haryana, known as a local commercial and agricultural hub in the Sonipat 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_69ca84dc04488190b9c91193976c0960 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda347b6bc8190a99b7dec1650cd46 completed April 1, 2026, 10:59 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1c43bccfc81909b940b180fe26626 completed April 5, 2026, 2:09 a.m.
NEDg Description generation batch_69d1c5e6a2f881908666328ce72a95ed completed April 5, 2026, 2:16 a.m.
NED2 Entity disambiguation (via description) batch_69d1c68311008190b2d5b8a2fadfba69 completed April 5, 2026, 2:18 a.m.
Created at: March 30, 2026, 8:28 p.m.