Triple

T17361224
Position Surface form Disambiguated ID Type / Status
Subject Xunantunich E422069 entity
Predicate firstDocumentedBy P108792 FINISHED
Object Thomas Gann NE NERFINISHED

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: Thomas Gann | Statement: [Xunantunich, firstDocumentedBy, Thomas Gann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Thomas Gann
Context triple: [Xunantunich, firstDocumentedBy, Thomas Gann]
  • A. Thomas Gann chosen
    Thomas Gann was a British medical doctor and pioneering archaeologist known for his early explorations and documentation of Maya ruins in Belize and Mexico.
  • B. Joseph Santley
    Joseph Santley was an American film director, producer, and screenwriter best known for his work on early sound comedies and musicals in Hollywood.
  • C. George Dixon
    George Dixon was a pioneering Canadian boxer of the late 19th century, recognized as the first Black world boxing champion and a trailblazer in the bantamweight and featherweight divisions.
  • D. George Dixon
    George Dixon was an 18th-century English sea captain and explorer known for his voyages to the Pacific Northwest coast of North America.
  • E. George Dixon
    George Dixon is a fictional London police constable best known as the kindly, old-fashioned bobby in the long-running British television series "Dixon of Dock Green."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889d520008190a26917a95bf1c2ea completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43a4d6de88190b816b93ff5778157 completed April 19, 2026, 2:13 a.m.
Created at: April 10, 2026, 5:44 a.m.