Triple

T19098571
Position Surface form Disambiguated ID Type / Status
Subject Mobile Infantry E467469 entity
Predicate enemy P4567 FINISHED
Object Skinnies NE NERFINISHED

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: Skinnies | Statement: [Mobile Infantry, enemy, Skinnies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Skinnies
Context triple: [Mobile Infantry, enemy, Skinnies]
  • A. Skinnies chosen
    Skinnies are an alien species in Robert A. Heinlein’s novel "Starship Troopers," initially allied with humanity’s enemies before becoming a notable faction in the interstellar war.
  • B. Yellowknives
    The Yellowknives are an Indigenous Dene (Athabaskan-speaking) people of Canada’s Northwest Territories, traditionally associated with the Yellowknife River and Great Slave Lake regions.
  • C. Mycoskie
    Mycoskie is the surname of Blake Mycoskie, the American entrepreneur best known as the founder of TOMS Shoes and pioneer of the “One for One” social entrepreneurship model.
  • D. Skids
    Skids is a Marvel Comics mutant character known for her frictionless force-field powers and association with the New Mutants and X-Factor.
  • E. Toughskins
    Toughskins is a durable children's clothing line best known for its long-lasting jeans and playwear once sold by Sears.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8dd05ac4c8190b1967d8f97f3fb2f completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e36c55688190b4a5135ea10c9924 completed April 20, 2026, 8:27 a.m.
Created at: April 10, 2026, 12:04 p.m.