Triple

T15471652
Position Surface form Disambiguated ID Type / Status
Subject Dura-Europos E376673 entity
Predicate majorExcavationsBy P33849 FINISHED
Object Yale University E20701 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: Yale University | Statement: [Dura-Europos, majorExcavationsBy, Yale University]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Yale University
Context triple: [Dura-Europos, majorExcavationsBy, Yale University]
  • A. Yale University chosen
    Yale University is an Ivy League research university in New Haven, Connecticut, renowned for its prestigious academic programs, historic campus, and influential alumni.
  • B. Yale
    Yale is a widely used romanization system for Cantonese Chinese that represents Cantonese sounds with the Latin alphabet.
  • C. Yale
    Yale is a historic town in British Columbia, Canada, that served as a key hub during the Cariboo Gold Rush and the construction of the Canadian Pacific Railway.
  • D. Yale
    Yale is a small unincorporated community located in Kansas, United States.
  • E. Yale College
    Yale College is the undergraduate liberal arts college of Yale University, offering a broad curriculum within a residential college system.
  • 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_69d85cd21dcc81908646251b1c26ea00 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f6c57308190b4cfe661c26addd4 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff2cf5d788819086a94af42c2ec21a completed May 9, 2026, 12:47 p.m.
Created at: April 10, 2026, 3:33 a.m.