Triple

T5380270
Position Surface form Disambiguated ID Type / Status
Subject Ascanius E113063 entity
Predicate associatedWithPlace P2830 FINISHED
Object Lavinium E200487 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: Lavinium | Statement: [Ascanius, associatedWithPlace, Lavinium]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lavinium
Context triple: [Ascanius, associatedWithPlace, Lavinium]
  • A. Lavinium chosen
    Lavinium was an ancient coastal city of Latium in central Italy, traditionally associated with the legendary landing of Aeneas and the early origins of Roman religious cults.
  • B. Lanuvium
    Lanuvium was an ancient Latin city in central Italy, noted for its important sanctuary of Juno Sospita and its later incorporation into the Roman state.
  • C. Falciano
    Falciano is a village and civil parish in the Republic of San Marino, forming part of the municipality of Serravalle.
  • D. Anicium
    Anicium is the historical Latin name of the French town now known as Le Puy-en-Velay.
  • E. Laurentum
    Laurentum was an ancient coastal city in Latium, traditionally associated with the legendary king Latinus and early Roman mythic history.
  • 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_69bd4436a1988190af18dcff7fd306b4 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd86ce56c88190a66b3852416edccb completed March 20, 2026, 5:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf2949cd9881908ca0d8fdf1642f71 completed March 21, 2026, 11:27 p.m.
Created at: March 20, 2026, 2:03 p.m.