Triple

T22649621
Position Surface form Disambiguated ID Type / Status
Subject Expo Application Services E559058 entity
Predicate hasComponent P35 FINISHED
Object EAS Build 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: EAS Build | Statement: [Expo Application Services, hasComponent, EAS Build]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: EAS Build
Context triple: [Expo Application Services, hasComponent, EAS Build]
  • A. EAS Build chosen
    EAS Build is Expo’s cloud-based build service that compiles React Native apps for iOS, Android, and web without requiring local native tooling.
  • B. Buildpack
    A buildpack is a modular set of scripts and configuration used to detect, compile, and prepare application code for deployment on platforms-as-a-service.
  • C. EAS
    EAS is a component of the Solar Wind Analyser instrument suite designed to measure and characterize electrons in the solar wind environment.
  • D. EAS
    EAS is the abbreviation commonly used for the Division of Engineering and Applied Science at the California Institute of Technology, encompassing its engineering and applied science research and academic programs.
  • E. EAS
    EAS is a regional leaders’ forum in the Asia-Pacific that focuses on strategic, political, and economic issues to promote stability and cooperation.
  • 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_69e245489dd88190b1f674acf61c8769 completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f1703b40b88190aec5cf2fa28bfcbf completed April 29, 2026, 2:43 a.m.
Created at: April 17, 2026, 3:05 p.m.