Triple

T17214330
Position Surface form Disambiguated ID Type / Status
Subject The Hobbit (1982 video game) E417812 entity
Predicate publisher P29 FINISHED
Object Addison-Wesley E5101 NE FINISHED

How this triple was built (2 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: Addison-Wesley | Statement: [The Hobbit (1982 video game), publisher, Addison-Wesley]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Addison-Wesley
Context triple: [The Hobbit (1982 video game), publisher, Addison-Wesley]
  • A. Addison-Wesley chosen
    Addison-Wesley is a prominent American publishing company known for its influential textbooks and professional books in science, engineering, and computer science.
  • B. Morgan Kaufmann
    Morgan Kaufmann is a prominent academic and professional publishing imprint known for influential books in computer science and engineering.
  • C. Wiley
    Wiley is a small unincorporated rural community located in Prowers County in southeastern Colorado.
  • D. Wiley
    Wiley is a masculine given name, often associated with notable American figures such as aviator Wiley Post.
  • E. Wiley
    Wiley is a pioneering British grime MC and producer, often dubbed the "Godfather of Grime" for his foundational role in shaping the genre.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d886d779488190b131369541c04e7d completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42dc8d3e88190a89bee6b75392360 completed April 19, 2026, 1:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a016751a5788190a385774d1ff002d0 completed May 11, 2026, 5:21 a.m.
Created at: April 10, 2026, 5:38 a.m.