Triple

T17374214
Position Surface form Disambiguated ID Type / Status
Subject Mandip Gill E422392 entity
Predicate name P16 FINISHED
Object Mandip Gill 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: Mandip Gill | Statement: [Mandip Gill, name, Mandip Gill]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mandip Gill
Context triple: [Mandip Gill, name, Mandip Gill]
  • A. Mandip Gill chosen
    Mandip Gill is a British actress best known for playing companion Yasmin Khan in the long-running science fiction series Doctor Who.
  • B. Parminder Nagra
    Parminder Nagra is a British actress best known for her breakthrough lead role in the football-themed film "Bend It Like Beckham" and for her later work in television dramas such as "ER."
  • C. Nikita Gill
    Nikita Gill is a contemporary British-Indian poet and writer known for her emotionally resonant, feminist poetry and modern retellings of myths and fairy tales.
  • D. Karan Patel
    Karan Patel is an Indian television actor best known for his role as Raman Bhalla in the popular Hindi TV series "Yeh Hai Mohabbatein."
  • E. Maheep Kapoor
    Maheep Kapoor is an Indian jewelry designer and reality television personality known for appearing on the Netflix series "Fabulous Lives of Bollywood Wives."
  • 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_69d889d6535c81908be333c01deaec4e completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a6b71148190bb10e1fac400d6c3 completed April 19, 2026, 2:14 a.m.
Created at: April 10, 2026, 5:44 a.m.