Triple

T8595951
Position Surface form Disambiguated ID Type / Status
Subject Thomas Melville E203544 entity
Predicate familyName P18 FINISHED
Object Melville E602455 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: Melville | Statement: [Thomas Melville, familyName, Melville]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Melville
Context triple: [Thomas Melville, familyName, Melville]
  • A. Melville
    Melville is a locality in New South Wales, Australia, situated near the rural area of Louth Park in the Hunter Region.
  • B. Melville chosen
    Melville is a Scottish surname most notably associated with the academic and suffragist Frances Priscilla Melville.
  • C. Melville
    Melville is a masculine given name most famously associated with the American novelist Herman Melville, author of "Moby-Dick."
  • D. Melville, New York
    Melville, New York is a suburban hamlet on Long Island known for its corporate offices, light industry, and residential communities within the town of Huntington.
  • E. Melvill
    Melvill is a surname most notably associated with the family of American novelist Herman Melville (born Melvill).
  • 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_69ca832a7f108190b4e4f5648abf4aa2 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cc46c945dc8190a313c61c0db46187 completed March 31, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69cea8d3fcfc8190bc51a38715ed453e completed April 2, 2026, 5:35 p.m.
Created at: March 30, 2026, 6:23 p.m.