Triple

T3235701
Position Surface form Disambiguated ID Type / Status
Subject Robert Smith E67849 entity
Predicate hasBrother P363 FINISHED
Object Samuel Smith E12681 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: Samuel Smith | Statement: [Robert Smith, hasBrother, Samuel Smith]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Samuel Smith
Context triple: [Robert Smith, hasBrother, Samuel Smith]
  • A. Samuel Smith chosen
    Samuel Smith was an American Revolutionary War and War of 1812 officer and politician who led the defense of Baltimore against the British in 1814.
  • B. Samuel Smith
    Samuel Smith was a London-based bookseller and publisher active in the early 18th century, known for issuing significant scientific works including Isaac Newton’s "Opticks."
  • C. Samuel Miller
    Samuel Miller was a prominent early 19th-century American Presbyterian theologian, educator, and church historian who helped shape Reformed theological education in the United States.
  • D. James Bailey
    James Bailey is a former American professional basketball player who played as a forward/center in the NBA, primarily known for his time with the Seattle SuperSonics and New Jersey Nets in the late 1970s and 1980s.
  • E. Samuel Barnes
    Samuel Barnes is an author known for his work with the Juicy brand.
  • 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_69ad858d27348190abb61c280b4c86a9 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaee05d34819095dbce4db6ac8613 completed March 8, 2026, 5:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28ea696a08190a17cbeeef7632977 completed March 12, 2026, 10 a.m.
Created at: March 8, 2026, 3:08 p.m.