Triple

T5108942
Position Surface form Disambiguated ID Type / Status
Subject John Carlyle E115166 entity
Predicate familyName P18 FINISHED
Object Carlyle E156422 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: Carlyle | Statement: [John Carlyle, familyName, Carlyle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carlyle
Context triple: [John Carlyle, familyName, Carlyle]
  • A. Carlyle chosen
    Carlyle is a Scottish surname most famously associated with the 19th-century essayist and historian Thomas Carlyle.
  • B. Bancroft
    Bancroft is an English-origin surname borne by various notable figures in politics, academia, and the arts.
  • C. Carlyle House
    Carlyle House is a historic 18th-century stone mansion and museum in Old Town Alexandria, Virginia, noted for its colonial architecture and role in early American history.
  • D. Dalrymple
    Dalrymple is a surname most notably associated with several Scottish nobles, politicians, and writers across history.
  • E. Erskine
    Erskine is a masculine given name of Scottish origin, traditionally used as both a first name and a surname.
  • 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_69bd4440b3348190be1251fd8b7951f1 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd75aa6b088190b02cdb66ec4a11f0 completed March 20, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69bebaa322d08190911dd2ca91405c3c completed March 21, 2026, 3:34 p.m.
Created at: March 20, 2026, 1:41 p.m.