Triple

T21548695
Position Surface form Disambiguated ID Type / Status
Subject William Jones Lowndes E531700 entity
Predicate familyName P18 FINISHED
Object Lowndes 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: Lowndes | Statement: [William Jones Lowndes, familyName, Lowndes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lowndes
Context triple: [William Jones Lowndes, familyName, Lowndes]
  • A. Lowndes chosen
    Lowndes is a surname most prominently associated with Australian racing driver Craig Lowndes.
  • B. Lowndes County
    Lowndes County is a rural county in central Alabama known for its significant role in the American civil rights movement, particularly during the Selma to Montgomery marches.
  • C. Troup
    Troup is a surname of Scottish origin borne by various notable individuals, including politicians, artists, and public figures.
  • D. Hale County
    Hale County is a rural county in west-central Alabama known for its agricultural landscape, small towns, and role in the Black Belt region.
  • E. Lamar County
    Lamar County is a rural county in western Alabama known for its small communities and agricultural landscape.
  • 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_69e0c45f17148190949c330ab9c27706 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb590bb0881908cd849096696db10 completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:28 p.m.