Triple

T226325
Position Surface form Disambiguated ID Type / Status
Subject Wilson E4321 entity
Predicate hasCognate P2525 FINISHED
Object Williams E4321 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: Williams | Statement: [Wilson, hasCognate, Williams]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Williams
Context triple: [Wilson, hasCognate, Williams]
  • A. Wilson chosen
    Wilson is a common English-language surname borne by numerous notable figures across fields such as science, politics, sports, and the arts.
  • B. Johnson
    Johnson is a common English surname borne by numerous notable individuals across politics, arts, sports, and other fields.
  • C. Clinton
    Clinton is a small town in Dutchess County, New York, known for its rural character and historic Hudson Valley setting.
  • D. Howard
    Howard is the middle name of Edwin H. Armstrong, the pioneering American electrical engineer and inventor of FM radio.
  • E. Howard
    Howard is a volume series of early U.S. Supreme Court case reports compiled by Benjamin Chew Howard, later incorporated into the official United States Reports.
  • 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_69a257363ffc81909757bde7ab3404da completed Feb. 28, 2026, 2:47 a.m.
NER Named-entity recognition batch_69a25c8d97d08190ad7c1c3e9322f34c completed Feb. 28, 2026, 3:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3cfe386d081908877b35b38bac0f5 completed March 1, 2026, 5:34 a.m.
Created at: Feb. 28, 2026, 2:53 a.m.