Triple

T22505446
Position Surface form Disambiguated ID Type / Status
Subject Editis E556376 entity
Predicate ownsImprint P139315 FINISHED
Object Pocket
Pocket is a French publishing imprint known for producing mass-market paperback editions of a wide range of fiction and non-fiction titles.
E1540656 NE FINISHED

How this triple was built (4 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: Pocket | Statement: [Editis, ownsImprint, Pocket]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pocket
Context triple: [Editis, ownsImprint, Pocket]
  • A. Pocket
    Pocket is a popular read-it-later service that lets users save articles, videos, and other web content for later viewing across devices.
  • B. The Pocket
    The Pocket is a small rural locality in the Byron Shire region of northern New South Wales, Australia, known for its lush hinterland setting near the coast.
  • C. Pocket B
    Pocket B is a residential sub-locality within the upscale South Delhi neighborhood of Vasant Kunj in India.
  • D. Pockets
    Pockets is a music producer known for contributing to Mos Def’s influential hip-hop album "Black on Both Sides."
  • E. In the Pocket
    "In the Pocket" is a 1976 soft rock album by singer-songwriter James Taylor, noted for its polished production and collaborations with artists like Stevie Wonder and Carly Simon.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Pocket
Triple: [Editis, ownsImprint, Pocket]
Generated description
Pocket is a French publishing imprint known for producing mass-market paperback editions of a wide range of fiction and non-fiction titles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pocket
Target entity description: Pocket is a French publishing imprint known for producing mass-market paperback editions of a wide range of fiction and non-fiction titles.
  • A. Pocket
    Pocket is a popular read-it-later service that lets users save articles, videos, and other web content for later viewing across devices.
  • B. The Pocket
    The Pocket is a small rural locality in the Byron Shire region of northern New South Wales, Australia, known for its lush hinterland setting near the coast.
  • C. Pocket B
    Pocket B is a residential sub-locality within the upscale South Delhi neighborhood of Vasant Kunj in India.
  • D. Pockets
    Pockets is a music producer known for contributing to Mos Def’s influential hip-hop album "Black on Both Sides."
  • E. In the Pocket
    "In the Pocket" is a 1976 soft rock album by singer-songwriter James Taylor, noted for its polished production and collaborations with artists like Stevie Wonder and Carly Simon.
  • F. None of above. chosen

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_69e11e555edc81909ca803587dafd747 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15d5bf0f0819093426d83ebd80ef0 completed April 29, 2026, 1:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b17e860888190b5c74df43a9890e9 completed May 18, 2026, 1:45 p.m.
NEDg Description generation batch_6a0b18ad4f608190a6947aeb790d8be7 completed May 18, 2026, 1:48 p.m.
NED2 Entity disambiguation (via description) batch_6a0b1979fe088190a06edb086d6b2b46 completed May 18, 2026, 1:51 p.m.
Created at: April 16, 2026, 8:50 p.m.