Triple

T13547611
Position Surface form Disambiguated ID Type / Status
Subject Axios E323552 entity
Predicate hasSubsidiary P254 FINISHED
Object Axios Pro E323552 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: Axios Pro | Statement: [Axios, hasSubsidiary, Axios Pro]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Axios Pro
Context triple: [Axios, hasSubsidiary, Axios Pro]
  • A. Axios
    Axios is a river god in Greek mythology, associated with the Axios (Vardar) River in the Balkans and counted among the Potamoi, the divine personifications of rivers.
  • B. Axios chosen
    Axios is a digital media company known for its concise, bullet-point-driven coverage of politics, business, technology, and media.
  • C. Exactum
    Exactum is a major university building on the University of Helsinki’s Kumpula Campus, primarily housing departments in mathematics, statistics, and computer science.
  • D. Axiom
    Axiom is the massive interstellar cruise ship in the animated film "WALL·E," where humanity lives in a state of perpetual leisure under the command of Captain B. McCrea.
  • E. Expa
    Expa is a startup studio and venture firm created by entrepreneur Garrett Camp to build and support early-stage technology companies.
  • 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_69d8076776248190bdf0d4fa1f85a5fc completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbafdb466881908fb46642dc66849d completed April 12, 2026, 2:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69f75da2c2008190b43a653a349ea0c7 completed May 3, 2026, 2:37 p.m.
Created at: April 9, 2026, 9:45 p.m.