Triple

T33886339
Position Surface form Disambiguated ID Type / Status
Subject Ashley Flowers E868642 entity
Predicate startedPodcast P27959 FINISHED
Object Crime Junkie in 2017
Crime Junkie in 2017 is a true crime podcast created and hosted by Ashley Flowers that quickly gained popularity for its narrative storytelling of real criminal cases.
 E2071224 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: Crime Junkie in 2017 | Statement: [Ashley Flowers, startedPodcast, Crime Junkie in 2017]
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: Crime Junkie in 2017
Triple: [Ashley Flowers, startedPodcast, Crime Junkie in 2017]
Generated description
Crime Junkie in 2017 is a true crime podcast created and hosted by Ashley Flowers that quickly gained popularity for its narrative storytelling of real criminal cases.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: startedPodcast
Context triple: [Ashley Flowers, startedPodcast, Crime Junkie in 2017]
  • A. hasPodcast chosen
    Indicates that an entity produces, owns, or is associated with a podcast.
  • B. startedNear
    Indicates that one event or action began close in time or space to another event or action.
  • C. broadcastBegan
    Indicates that the transmission or airing of a broadcast has started.
  • D. podcastTitle
    Indicates the title assigned to a particular podcast.
  • E. podcastPlatform
    Indicates that one entity serves as the platform or service on which the other entity’s podcast is hosted, distributed, or made available.
  • F. None of above.

Provenance (6 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_69f34996761c8190864e42f7c9cf215b completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69fff09dae088190bd8460060d778feb completed May 10, 2026, 2:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a3676321d0081908d6e4275aa79e457 completed June 20, 2026, 11:14 a.m.
NEDg Description generation batch_6a3676f702e48190afa2ce8b400a4a8d completed June 20, 2026, 11:18 a.m.
NED2 Entity disambiguation (via description) batch_6a36776a62848190ae95f5ba56ea5e43 completed June 20, 2026, 11:20 a.m.
PD Predicate disambiguation batch_69fff0027c5c8190baa5c7a15852cbe0 completed May 10, 2026, 2:40 a.m.
Created at: May 1, 2026, 1:48 a.m.