Triple

T1729988
Position Surface form Disambiguated ID Type / Status
Subject Todai E37587 entity
Predicate shortName P43 FINISHED
Object Todai E37587 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: Todai | Statement: [Todai, shortName, Todai]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Todai
Context triple: [Todai, shortName, Todai]
  • A. Todai chosen
    Todai is the common nickname for the University of Tokyo, Japan’s most prestigious and influential national research university.
  • B. Tokyo Daigaku
    Tokyo Daigaku, commonly known as the University of Tokyo, is Japan’s most prestigious national research university and a leading institution in higher education and scholarship in Asia.
  • C. Misurata University
    Misurata University is a public higher education institution in the city of Misrata, Libya, offering a range of undergraduate and postgraduate programs across multiple disciplines.
  • D. Keijo Imperial University
    Keijo Imperial University was a Japanese imperial university established in colonial Korea that served as a major center for higher education and research under Japanese rule.
  • E. Setsunan University
    Setsunan University is a private Japanese university located in Osaka Prefecture, known for its programs in engineering, pharmacy, and law.
  • 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_69a8861acab88190bb43cde203429399 completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69aa637f202c8190b46a31bef51465c8 completed March 6, 2026, 5:17 a.m.
NED1 Entity disambiguation (via context triple) batch_69b44eb4706c8190870d99abc140973d completed March 13, 2026, 5:51 p.m.
Created at: March 4, 2026, 7:30 p.m.