Triple

T1884759
Position Surface form Disambiguated ID Type / Status
Subject Ionic order E39937 entity
Predicate influenced P9 FINISHED
Object Composite order E192250 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: Composite order | Statement: [Ionic order, influenced, Composite order]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Composite order
Context triple: [Ionic order, influenced, Composite order]
  • A. Composite order chosen
    The Composite order is a classical architectural style that combines elements of the Ionic and Corinthian orders, most notably featuring volutes and acanthus leaves in its ornate capitals.
  • B. Composite
    Composite is a structural design pattern that lets you treat individual objects and compositions of objects uniformly by organizing them into tree-like hierarchies.
  • C. ONE Order
    ONE Order is an IATA initiative that modernizes airline retailing and order management by replacing traditional PNR, ticket, and EMD records with a single, customer-centric order.
  • D. Ionic order
    The Ionic order is one of the classical Greek architectural styles, distinguished by its slender, fluted columns and scrolled volute capitals, widely revived in later Western architecture.
  • E. Combine
    Combine is Apple’s declarative reactive programming framework for handling asynchronous events and data streams in Swift applications.
  • 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_69a88633e4fc8190b7eb40463e048ec5 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb11eb2d0819088d67b1cfc772049 completed March 7, 2026, 5:01 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf61413081909c0e840590aaf631 completed March 8, 2026, 8:43 p.m.
Created at: March 4, 2026, 7:34 p.m.