Triple

T16272651
Position Surface form Disambiguated ID Type / Status
Subject Bobby Bedi E395039 entity
Predicate notableWork P4 FINISHED
Object Saathiya E1202116 NE FINISHED

How this triple was built (2 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: Saathiya | Statement: [Bobby Bedi, notableWork, Saathiya]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saathiya
Context triple: [Bobby Bedi, notableWork, Saathiya]
  • A. Saathiya chosen
    Saathiya is a 2002 Hindi romantic drama film, directed by Shaad Ali and produced by Yash Raj Films, known for its realistic portrayal of modern marriage and its popular A.R. Rahman soundtrack.
  • B. Nawayathi
    Nawayathi is an Indo-Aryan language variety spoken by the Nawayath Muslim community, primarily along the coastal regions of Karnataka in southwestern India.
  • C. Tarpeena
    Tarpeena is a small rural town and locality in South Australia, known historically for its timber and forestry industries.
  • D. Shivini
    Shivini is the Urartian sun god, often associated with light, justice, and royal authority in the ancient Kingdom of Urartu.
  • E. Raakh
    Raakh is a 1989 Indian neo-noir crime drama film, acclaimed for its gritty storytelling and performances, and regarded as a cult classic in Hindi cinema.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d87f221d8081909b0b2063e7528ba2 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2460a4f7c8190a614c11f7eaa0a7a completed April 17, 2026, 2:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0017bf09888190b3d90db3517a2f1e completed May 10, 2026, 5:29 a.m.
Created at: April 10, 2026, 5:05 a.m.