Triple

T2549458
Position Surface form Disambiguated ID Type / Status
Subject Orion Publishing Group E57986 entity
Predicate hasImprint P2763 FINISHED
Object Orion Dash
Orion Dash is a digital-first imprint of the Orion Publishing Group that focuses on commercial fiction and genre titles.
E276537 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: Orion Dash | Statement: [Orion Publishing Group, hasImprint, Orion Dash]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orion Dash
Context triple: [Orion Publishing Group, hasImprint, Orion Dash]
  • A. Orion
    Orion is a prominent constellation in the night sky, easily recognized by its three-star belt and associated in many cultures with the figure of a hunter.
  • B. Antares
    Antares was the Lunar Module used in NASA’s Apollo 14 mission to land astronauts on the Moon in 1971.
  • C. Thunderbird
    Thunderbird is a free, open-source email client developed by Mozilla, known for its extensibility and cross-platform support.
  • D. Thunderhawk
    Thunderhawk is a suspended looping steel roller coaster at Michigan’s Adventure amusement park in Muskegon, Michigan.
  • E. Thar
    Thar is a city located in Saudi Arabia’s Najran Region, near the country’s southern border.
  • 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: Orion Dash
Triple: [Orion Publishing Group, hasImprint, Orion Dash]
Generated description
Orion Dash is a digital-first imprint of the Orion Publishing Group that focuses on commercial fiction and genre titles.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Orion Dash
Target entity description: Orion Dash is a digital-first imprint of the Orion Publishing Group that focuses on commercial fiction and genre titles.
  • A. Orion
    Orion is a prominent constellation in the night sky, easily recognized by its three-star belt and associated in many cultures with the figure of a hunter.
  • B. Antares
    Antares was the Lunar Module used in NASA’s Apollo 14 mission to land astronauts on the Moon in 1971.
  • C. Thunderbird
    Thunderbird is a free, open-source email client developed by Mozilla, known for its extensibility and cross-platform support.
  • D. Thunderhawk
    Thunderhawk is a suspended looping steel roller coaster at Michigan’s Adventure amusement park in Muskegon, Michigan.
  • E. Thar
    Thar is a city located in Saudi Arabia’s Najran Region, near the country’s southern border.
  • 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_69ab4a5212d88190b989ce129f2ad87f completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abd2e7cd4c8190a52cbbf1229441a6 completed March 7, 2026, 7:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69af5d114964819092b847c701a0704e completed March 9, 2026, 11:51 p.m.
NEDg Description generation batch_69af5db1c290819099d88815ebe97c1b completed March 9, 2026, 11:54 p.m.
NED2 Entity disambiguation (via description) batch_69af5e2cd2588190bc24c3cdd350fa70 completed March 9, 2026, 11:56 p.m.
Created at: March 6, 2026, 9:47 p.m.