Triple

T33702134
Position Surface form Disambiguated ID Type / Status
Subject Greed E863484 entity
Predicate productionCompany P490 FINISHED
Object Sony Pictures International Productions
Sony Pictures International Productions is a division of Sony Pictures that develops and produces local-language films and content for international markets.
E2062636 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: Sony Pictures International Productions | Statement: [Greed, productionCompany, Sony Pictures International Productions]
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: Sony Pictures International Productions
Triple: [Greed, productionCompany, Sony Pictures International Productions]
Generated description
Sony Pictures International Productions is a division of Sony Pictures that develops and produces local-language films and content for international markets.

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_69f3498723a08190ac034339cc78eade completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69f6fa8d59b88190832e66716f7170ab completed May 3, 2026, 7:34 a.m.
NED1 Entity disambiguation (via context triple) batch_6a363c9f949c819083e0a643f79c235a completed June 20, 2026, 7:09 a.m.
NEDg Description generation batch_6a36445bcf1081909ec9818c4216f159 completed June 20, 2026, 7:42 a.m.
NED2 Entity disambiguation (via description) batch_6a3645556948819096b5d8722039659a completed June 20, 2026, 7:46 a.m.
Created at: May 1, 2026, 1:43 a.m.