Triple

T4822769
Position Surface form Disambiguated ID Type / Status
Subject Harvard House E107747 entity
Predicate associatedWith P37 FINISHED
Object John Harvard E103 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: John Harvard | Statement: [Harvard House, associatedWith, John Harvard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Harvard
Context triple: [Harvard House, associatedWith, John Harvard]
  • A. John Harvard chosen
    John Harvard was a 17th-century English clergyman and benefactor whose substantial bequest helped establish the institution that became Harvard University.
  • B. Thomas Harvard
    Thomas Harvard was a 17th-century Englishman known primarily as the brother of John Harvard, the clergyman and benefactor after whom Harvard University is named.
  • C. Elihu Yale
    Elihu Yale was an 18th-century British merchant and philanthropist whose donations to a colonial college in New Haven led to that institution being renamed Yale University in his honor.
  • D. Christopher Newport
    Christopher Newport was an English seaman and privateer best known for commanding the 1607 voyage that founded the Jamestown colony in Virginia.
  • E. Charles Eliot
    Charles Eliot was a prominent American landscape architect of the late 19th century, known for his influential work in urban park and parkway design around Boston.
  • 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_69bd43f9efa081908314cb3e94fa1695 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6caa95ec8190bea525dbf3a00477 completed March 20, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4dc6ddcc8190903c0737476bbe36 completed March 21, 2026, 7:50 a.m.
Created at: March 20, 2026, 1:24 p.m.