Triple

T35365393
Position Surface form Disambiguated ID Type / Status
Subject Thanksgiving (2023 film) E1021614 entity
Predicate productionCompany P490 FINISHED
Object Spyglass Media Group
Spyglass Media Group is an American film and television production company known for backing genre and mainstream commercial projects, including modern horror and thriller releases.
E2138810 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: Spyglass Media Group | Statement: [Thanksgiving (2023 film), productionCompany, Spyglass Media Group]
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: Spyglass Media Group
Triple: [Thanksgiving (2023 film), productionCompany, Spyglass Media Group]
Generated description
Spyglass Media Group is an American film and television production company known for backing genre and mainstream commercial projects, including modern horror and thriller releases.

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_69f76df000488190ab7c97f565677055 completed May 3, 2026, 3:46 p.m.
NER Named-entity recognition batch_69f791d200a08190b850623d264de4ff completed May 3, 2026, 6:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a382cb38b3c8190b977b2a7b974aaf9 completed June 21, 2026, 6:25 p.m.
NEDg Description generation batch_6a382d58e2b48190a1070bedf3aa5fff completed June 21, 2026, 6:28 p.m.
NED2 Entity disambiguation (via description) batch_6a382e1f37188190ac188d12cc6dce07 completed June 21, 2026, 6:31 p.m.
Created at: May 3, 2026, 4:03 p.m.