Triple

T35944021
Position Surface form Disambiguated ID Type / Status
Subject The Toolbox Murders (1978 film) E1039535 entity
Predicate director P255 FINISHED
Object Dennis Donnelly
Dennis Donnelly is an American film and television director best known for helming the 1978 cult horror film "The Toolbox Murders."
E2172039 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: Dennis Donnelly | Statement: [The Toolbox Murders (1978 film), director, Dennis Donnelly]
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: Dennis Donnelly
Triple: [The Toolbox Murders (1978 film), director, Dennis Donnelly]
Generated description
Dennis Donnelly is an American film and television director best known for helming the 1978 cult horror film "The Toolbox Murders."

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_69f76e24bbd0819096b837d35371639a completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f7abb141b08190ad4a151ed89badf7 completed May 3, 2026, 8:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a390d30d510819091500ae2f624bcfc completed June 22, 2026, 10:23 a.m.
NEDg Description generation batch_6a390eaab52881909027bbc2cc2469ba completed June 22, 2026, 10:30 a.m.
NED2 Entity disambiguation (via description) batch_6a390f6f1ec88190b2fe251699996657 completed June 22, 2026, 10:33 a.m.
Created at: May 3, 2026, 4:07 p.m.