Triple

T17348772
Position Surface form Disambiguated ID Type / Status
Subject ERIC E421752 entity
Predicate acronym P43 FINISHED
Object ERIC NE ONNED1

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: ERIC | Statement: [ERIC, acronym, ERIC]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ERIC
Context triple: [ERIC, acronym, ERIC]
  • A. ERIC chosen
    ERIC is a comprehensive digital library of education-related literature and resources maintained by the U.S. Department of Education.
  • B. ERIC
    ERIC is the stock ticker symbol for Ericsson, a major Swedish multinational telecommunications and networking company.
  • C. ETS
    ETS is a nonprofit organization that develops and administers standardized tests and assessments used worldwide for education, certification, and professional licensing.
  • D. ETS
    ETS is the abbreviation for the Educational and Training Services Branch, a unit responsible for developing and delivering education and training programs.
  • E. ETS
    ETS is the public transit brand serving the city of Edmonton, Alberta, encompassing its network of buses, light rail, and related transportation services.
  • 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a2af5f88190b4c292ca30993b36 completed April 19, 2026, 2:12 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01955658b88190bce3fb2b5738afc6 in_progress May 11, 2026, 8:37 a.m.
Created at: April 10, 2026, 5:44 a.m.