Triple

T16631803
Position Surface form Disambiguated ID Type / Status
Subject Picenes E404096 entity
Predicate neighbor P350 FINISHED
Object Sabines E44501 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: Sabines | Statement: [Picenes, neighbor, Sabines]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sabines
Context triple: [Picenes, neighbor, Sabines]
  • A. Sabines chosen
    The Sabines were an ancient Italic people of central Italy, closely associated with early Roman history and culture.
  • B. Senones
    The Senones were an ancient Gallic tribe known for their settlements in central Italy and Gaul and for their role in early conflicts with the Roman Republic.
  • C. Bruttians
    The Bruttians were an ancient Italic people of southern Italy, known for their role in regional conflicts during the Hellenistic and Roman periods.
  • D. Suessiones
    The Suessiones were an ancient Celtic tribe of northern Gaul, known from Julius Caesar’s accounts as one of the principal Belgic peoples during the Gallic Wars.
  • E. Sabiny
    The Sabiny are an indigenous Nilotic-speaking ethnic group primarily inhabiting the mountainous areas of eastern Uganda, particularly around Mount Elgon.
  • 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_69d883897eb481909eaaa088ba9918d9 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e378e704c08190a28286ac12165ea5 completed April 18, 2026, 12:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a008a2b3a608190ad8d2b653cd8785d completed May 10, 2026, 1:37 p.m.
Created at: April 10, 2026, 5:17 a.m.