Triple

T144428
Position Surface form Disambiguated ID Type / Status
Subject Thomas Harvard E2922 entity
Predicate relative 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: [Thomas Harvard, relative, John Harvard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Harvard
Context triple: [Thomas Harvard, relative, 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. Robert Harvard
    Robert Harvard was the father of John Harvard, the English clergyman whose bequest helped found Harvard College in colonial America.
  • D. Increase Mather
    Increase Mather was a prominent 17th-century New England Puritan minister and political leader who played a major role in colonial religious life and governance, including efforts to curb the excesses of the Salem witch trials.
  • E. James Bowdoin
    James Bowdoin was an 18th-century American political leader, scholar, and governor of Massachusetts who played a key role in the intellectual and civic life of the early United States.
  • 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_69a2521e35c08190b28e5c9f1e3c9b59 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257e935bc8190a03e54a10e9ba6f7 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a35e9e2b8c8190913c083e841c98d8 completed Feb. 28, 2026, 9:31 p.m.
Created at: Feb. 28, 2026, 2:31 a.m.