Triple

T22433331
Position Surface form Disambiguated ID Type / Status
Subject Hotel Salvation E554550 entity
Predicate stars P1956 FINISHED
Object Geetanjali Kulkarni NE NERFINISHED

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: Geetanjali Kulkarni | Statement: [Hotel Salvation, stars, Geetanjali Kulkarni]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Geetanjali Kulkarni
Context triple: [Hotel Salvation, stars, Geetanjali Kulkarni]
  • A. Geetanjali Kulkarni chosen
    Geetanjali Kulkarni is an Indian actress acclaimed for her powerful performances in independent and parallel cinema, particularly in Marathi and Hindi films.
  • B. Namita Sinha
    Namita Sinha is an actress known for her role in the Bengali film "Harano Sur."
  • C. Namita Gokhale
    Namita Gokhale is an Indian writer, publisher, and literary curator best known for her novels and for shaping contemporary literary culture in India.
  • D. Vyjayanti Iyer
    Vyjayanti Iyer is a central character in the 1993 Hindi romantic comedy film "Hum Hain Rahi Pyar Ke," known for her spirited and endearing role in the story.
  • E. Kiran Nagarkar
    Kiran Nagarkar was an acclaimed Indian novelist, playwright, and screenwriter known for his innovative, multilingual works such as "Cuckold" and "Ravan and Eddie."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e5010e48190ae1e9c9db9697637 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15a3320448190ae3931062599116e completed April 29, 2026, 1:09 a.m.
Created at: April 16, 2026, 8:47 p.m.