Triple

T3921760
Position Surface form Disambiguated ID Type / Status
Subject Ephs E88974 entity
Predicate namedAfter P63 FINISHED
Object Ephraim Williams E166056 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: Ephraim Williams | Statement: [Ephs, namedAfter, Ephraim Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ephraim Williams
Context triple: [Ephs, namedAfter, Ephraim Williams]
  • A. Ephraim Williams chosen
    Ephraim Williams was an 18th-century American soldier and landowner whose bequest led to the establishment of Williams College in Massachusetts.
  • B. Ephraim Hart
    Ephraim Hart was an early American merchant and broker who was among the founders of what became the New York Stock Exchange.
  • C. Ephraim Bull
    Ephraim Bull was a 19th-century American horticulturist best known for developing the Concord grape, one of the first widely successful American table and wine grapes.
  • D. Enoch Poor
    Enoch Poor was an American Revolutionary War brigadier general from New Hampshire who distinguished himself in multiple key campaigns, including the Saratoga and Monmouth battles.
  • E. Samuel Blatchford
    Samuel Blatchford was an Associate Justice of the U.S. Supreme Court in the late 19th century, known for his expertise in admiralty and patent 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_69aed955229881909e85e73ffab1d343 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed7a553c81909b65f8287293ecac completed March 9, 2026, 3:55 p.m.
NED1 Entity disambiguation (via context triple) batch_69b56284b2708190858e830355f3ff24 completed March 14, 2026, 1:28 p.m.
Created at: March 9, 2026, 3:22 p.m.