Triple

T10689113
Position Surface form Disambiguated ID Type / Status
Subject Agilulf E251961 entity
Predicate ethnicity P194 FINISHED
Object Lombard E790434 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: Lombard | Statement: [Agilulf, ethnicity, Lombard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lombard
Context triple: [Agilulf, ethnicity, Lombard]
  • A. Lombard
    Lombard is a suburban village in DuPage County, Illinois, located west of Chicago and known as the "Lilac Village" for its annual Lilac Festival and historic Lilacia Park.
  • B. Lombard
    Lombard is a Gallo-Italic Romance language traditionally spoken in and around Milan and across much of Lombardy in northern Italy.
  • C. Lombard Italy chosen
    Lombard Italy was the early medieval kingdom in the Italian peninsula ruled by the Germanic Lombards from the 6th to 8th centuries, known for its distinctive legal traditions and role as a successor state to the Western Roman Empire.
  • D. Lombardijen
    Lombardijen is a residential neighborhood in the IJsselmonde borough of Rotterdam in the Netherlands.
  • E. Brescian
    Brescian is a variety of the Lombard language traditionally spoken in and around the city of Brescia in northern Italy.
  • 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_69d6aa5bd7c08190a816e733b4045c23 completed April 8, 2026, 7:19 p.m.
NER Named-entity recognition batch_69d6fd1aef888190ba92474af3a49e36 completed April 9, 2026, 1:12 a.m.
NED1 Entity disambiguation (via context triple) batch_69d9889d1f988190938be54771161b00 completed April 10, 2026, 11:32 p.m.
Created at: April 8, 2026, 9:11 p.m.