Triple

T748638
Position Surface form Disambiguated ID Type / Status
Subject Williams College E15397 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: [Williams College, namedAfter, Ephraim Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ephraim Williams
Context triple: [Williams College, 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. Samuel Ellis
    Samuel Ellis was the landowner after whom Ellis Island in New York Harbor was named.
  • D. Moses Taylor
    Moses Taylor was a prominent 19th-century American merchant, banker, and railroad executive who became one of the wealthiest men of his era.
  • E. Jeremiah Elfreth
    Jeremiah Elfreth was an 18th-century Philadelphia blacksmith and property owner whose name was given to the historic residential street now known as Elfreth's Alley.
  • 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_69a49358aa308190adbc9b5a0a2adcf9 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4a62f31888190b80cb0a7220f8d80 completed March 1, 2026, 8:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad0e56e7fc8190a81cbd97e20fd0e6 completed March 8, 2026, 5:51 a.m.
Created at: March 1, 2026, 7:37 p.m.