Triple

T36028390
Position Surface form Disambiguated ID Type / Status
Subject Tom Spanbauer E1042192 entity
Predicate hasWritingWorkshop P184497 FINISHED
Object Dangerous Writing
Dangerous Writing is Tom Spanbauer’s influential minimalist fiction workshop and literary approach that emphasizes radical honesty, vulnerability, and stripped-down prose.
E2164311 NE FINISHED

How this triple was built (3 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: Dangerous Writing | Statement: [Tom Spanbauer, hasWritingWorkshop, Dangerous Writing]
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: Dangerous Writing
Triple: [Tom Spanbauer, hasWritingWorkshop, Dangerous Writing]
Generated description
Dangerous Writing is Tom Spanbauer’s influential minimalist fiction workshop and literary approach that emphasizes radical honesty, vulnerability, and stripped-down prose.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasWritingWorkshop
Context triple: [Tom Spanbauer, hasWritingWorkshop, Dangerous Writing]
  • A. hasWrittenWorkType
    Indicates that an entity (typically a written work) is associated with a specific type or category of written work (such as novel, article, report, etc.).
  • B. hasWrittenFor
    Indicates that one entity has created written content (such as articles, stories, or texts) for or on behalf of another entity, typically a publication, organization, or platform.
  • C. usesWriting
    Indicates that one entity employs or applies a particular writing system, script, or written form for communication or representation.
  • D. usesWritingCenter
    Indicates that an entity makes use of the services or resources provided by a writing center.
  • E. willWrittenIn
    Indicates that a legal will was authored, drafted, or formally written in a specified location or jurisdiction.
  • F. None of above. chosen

Provenance (7 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_69f76e2c568881909e1e21f85252b0f0 completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_69f7b35e32d481909ef0220e6f6ff4a8 completed May 3, 2026, 8:43 p.m.
NED1 Entity disambiguation (via context triple) batch_6a38c005d5e08190908f13b44475161e completed June 22, 2026, 4:54 a.m.
NEDg Description generation batch_6a38c089e8908190808360aad00f1c35 completed June 22, 2026, 4:56 a.m.
NED2 Entity disambiguation (via description) batch_6a38c0f110348190b121e0a0b38aee30 completed June 22, 2026, 4:58 a.m.
PD Predicate disambiguation batch_69f7b1bad2e88190963ab4ee5d4f2038 completed May 3, 2026, 8:36 p.m.
PDg Predicate description generation batch_69f7b2c66054819083897e25edb65ba7 completed May 3, 2026, 8:40 p.m.
Created at: May 3, 2026, 4:07 p.m.