Triple

T13657758
Position Surface form Disambiguated ID Type / Status
Subject Rod Library E326905 entity
Predicate abbreviation P43 FINISHED
Object UNI Rod Library E326905 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: UNI Rod Library | Statement: [Rod Library, abbreviation, UNI Rod Library]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: UNI Rod Library
Context triple: [Rod Library, abbreviation, UNI Rod Library]
  • A. RODN
    RODN is the ICAO airport code for Kadena Air Base, a major United States Air Force installation on Okinawa, Japan.
  • B. Radox
    Radox is a well-known personal care brand, particularly recognized for its bath and shower products such as bubble baths and shower gels.
  • C. Rod Library chosen
    Rod Library is the main academic library of the University of Northern Iowa, providing research resources, study spaces, and information services to students and faculty.
  • D. Roden
    Roden is a town in the Dutch province of Drenthe known as a local service and population center within the municipality of Noordenveld.
  • E. Roden
    Roden is a Czech surname most notably borne by actor Karel Roden, known for his work in both Czech and international films.
  • 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_69d8076d8270819092afc2f0e9c359a8 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dbc61d56e4819084ae3c16ecdf4a05 completed April 12, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f78b06c5d081909d31b8a537c94edb completed May 3, 2026, 5:51 p.m.
Created at: April 9, 2026, 9:52 p.m.