Triple

T28031550
Position Surface form Disambiguated ID Type / Status
Subject Deep Blue Sea 2 E708281 entity
Predicate writer P1360 FINISHED
Object Erik Patterson
Erik Patterson is a screenwriter known for his work on genre films, including the sci-fi horror sequel "Deep Blue Sea 2."
E1820689 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: Erik Patterson | Statement: [Deep Blue Sea 2, writer, Erik Patterson]
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: Erik Patterson
Triple: [Deep Blue Sea 2, writer, Erik Patterson]
Generated description
Erik Patterson is a screenwriter known for his work on genre films, including the sci-fi horror sequel "Deep Blue Sea 2."

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_69ef9b6bdd9c8190bb3a574a03774ad1 completed April 27, 2026, 5:22 p.m.
NER Named-entity recognition batch_69f63c72207481909a00938678ab7005 completed May 2, 2026, 6:03 p.m.
NED1 Entity disambiguation (via context triple) batch_6a16415dbd288190bab4071d7f00e54f completed May 27, 2026, 12:57 a.m.
NEDg Description generation batch_6a164240e9308190aa46c9b0745446b7 completed May 27, 2026, 1 a.m.
NED2 Entity disambiguation (via description) batch_6a16467e0a3c8190aba09c9f0a65298c completed May 27, 2026, 1:18 a.m.
Created at: April 27, 2026, 8:17 p.m.