Triple

T2875735
Position Surface form Disambiguated ID Type / Status
Subject Tohoku University E56872 entity
Predicate motto P42 FINISHED
Object Research First E53573 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: Research First | Statement: [Tohoku University, motto, Research First]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Research First
Context triple: [Tohoku University, motto, Research First]
  • A. Research First chosen
    Research First is the guiding motto of Tohoku University, emphasizing the institution’s primary commitment to advancing scholarly inquiry and innovation.
  • B. Research Bureau
    The Research Bureau is an internal analytical and policy research department of the People's Bank of China that supports monetary and financial decision-making.
  • C. Search and Discovery
    Search and Discovery is a regular Physics Today section that highlights notable recent advances and findings across the physical sciences.
  • D. Case Research Laboratory
    The Case Research Laboratory was an early 20th-century research facility best known for pioneering work in sound-on-film motion picture technology.
  • E. Digital Research
    Digital Research was a pioneering software company best known for creating early microcomputer operating systems such as CP/M and its 16-bit variants.
  • 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_69ab4a4ced288190ab6d3e062d10f7f6 completed March 6, 2026, 9:42 p.m.
NER Named-entity recognition batch_69abe004a64481908f1897d9054a7368 completed March 7, 2026, 8:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69b01dbb28588190ba2daae192744908 completed March 10, 2026, 1:33 p.m.
Created at: March 6, 2026, 10:03 p.m.