Triple

T37109391
Position Surface form Disambiguated ID Type / Status
Subject Salt (2010 film) E918943 entity
Predicate producer P490 FINISHED
Object Sunil Perkash
Sunil Perkash is a film producer best known for his work on major Hollywood action and fantasy movies, including the Angelina Jolie–led thriller "Salt."
E830865 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: Sunil Perkash | Statement: [Salt (2010 film), producer, Sunil Perkash]
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: Sunil Perkash
Triple: [Salt (2010 film), producer, Sunil Perkash]
Generated description
Sunil Perkash is a film producer best known for his work on major Hollywood action and fantasy movies, including the Angelina Jolie–led thriller "Salt."

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_69f76e9b99c8819096164b21ff5bd996 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69fb2ff600a881909efae58de1f4ce11 completed May 6, 2026, 12:11 p.m.
NED1 Entity disambiguation (via context triple) batch_6a40fb62b5a88190ba897880548a8629 completed June 28, 2026, 10:45 a.m.
NEDg Description generation batch_6a40fc57c3608190ab0313ad2f9d1263 completed June 28, 2026, 10:49 a.m.
NED2 Entity disambiguation (via description) batch_6a40fcb794b48190828c38f5033084d4 completed June 28, 2026, 10:51 a.m.
Created at: May 3, 2026, 4:14 p.m.