Triple

T15711936
Position Surface form Disambiguated ID Type / Status
Subject Blue Ruin E380859 entity
Predicate producer P490 FINISHED
Object Anish Savjani E115983 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: Anish Savjani | Statement: [Blue Ruin, producer, Anish Savjani]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Anish Savjani
Context triple: [Blue Ruin, producer, Anish Savjani]
  • A. Anish Savjani chosen
    Anish Savjani is an American film producer known for his work on acclaimed independent films, including the thriller "Green Room."
  • B. Bhavit Sheth
    Bhavit Sheth is an Indian entrepreneur best known as the co-founder of Dream Sports, the parent company of fantasy sports platform Dream11.
  • C. Kartikeya Sarabhai
    Kartikeya Sarabhai is an Indian environmental educator and sustainability advocate, known for his leadership in environmental education and for being the son of space scientist Vikram Sarabhai.
  • D. Hiten Patel
    Hiten Patel is an actor who appeared in the British television drama film "The Boy with the Topknot."
  • E. Harish Patel
    Harish Patel is an Indian character actor known for his extensive work in Hindi cinema and television, as well as for appearing in international projects such as Marvel’s Eternals.
  • 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_69d86d9bf930819082b30cf6d169297c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f8f5d6081908243fa59b46b7c76 completed April 16, 2026, 2:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff757f571881908015fe68df2a5e69 completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:45 a.m.