Triple

T622758
Position Surface form Disambiguated ID Type / Status
Subject Little, Brown and Company E14548 entity
Predicate hasImprint P2763 FINISHED
Object Orbit
Orbit is a publishing imprint best known for releasing science fiction and fantasy books.
 E77992 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: Orbit | Statement: [Little, Brown and Company, hasImprint, Orbit]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Orbit
Context triple: [Little, Brown and Company, hasImprint, Orbit]
  • A. Kepler Track
    The Kepler Track is a renowned multi-day Great Walk in New Zealand, offering alpine and lakeside scenery in the Fiordland region of the South Island.
  • B. Kosmos
    Kosmos is Alexander von Humboldt’s multi-volume work that presents a comprehensive scientific and philosophical overview of the natural world and the universe.
  • C. Comet
    Comet is one of Santa Claus’s traditional flying reindeer, often depicted as swift and spirited as he helps pull Santa’s sleigh on Christmas Eve.
  • D. 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.
  • E. Eclipse
    Eclipse is a widely used open-source integrated development environment (IDE) primarily for Java and other programming languages, known for its extensible plugin-based architecture.
  • 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: Orbit
Triple: [Little, Brown and Company, hasImprint, Orbit]
Generated description
Orbit is a publishing imprint best known for releasing science fiction and fantasy books.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Orbit
Target entity description: Orbit is a publishing imprint best known for releasing science fiction and fantasy books.
  • A. Kepler Track
    The Kepler Track is a renowned multi-day Great Walk in New Zealand, offering alpine and lakeside scenery in the Fiordland region of the South Island.
  • B. Kosmos
    Kosmos is Alexander von Humboldt’s multi-volume work that presents a comprehensive scientific and philosophical overview of the natural world and the universe.
  • C. Comet
    Comet is one of Santa Claus’s traditional flying reindeer, often depicted as swift and spirited as he helps pull Santa’s sleigh on Christmas Eve.
  • D. 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.
  • E. Eclipse
    Eclipse is a widely used open-source integrated development environment (IDE) primarily for Java and other programming languages, known for its extensible plugin-based architecture.
  • 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_69a4934b17c881909ace8270e8ddd202 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49e402d9c8190936896e3ebb6edc5 completed March 1, 2026, 8:14 p.m.
NED1 Entity disambiguation (via context triple) batch_69a563cab73c819082b51d64d249143b completed March 2, 2026, 10:17 a.m.
NEDg Description generation batch_69a5657b51c881909c393f79c359181c completed March 2, 2026, 10:24 a.m.
NED2 Entity disambiguation (via description) batch_69a565e528a88190a547f69c7e378140 completed March 2, 2026, 10:26 a.m.
Created at: March 1, 2026, 7:35 p.m.