Triple

T33319287
Position Surface form Disambiguated ID Type / Status
Subject Miracle of the Thundering Legion E853094 entity
Predicate hasLocationApproximation P22067 FINISHED
Object region of the Danube frontier LITERAL 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: region of the Danube frontier | Statement: [Miracle of the Thundering Legion, hasLocationApproximation, region of the Danube frontier]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasLocationApproximation
Context triple: [Miracle of the Thundering Legion, hasLocationApproximation, region of the Danube frontier]
  • A. hasApproximateLocation chosen
    Indicates that an entity is associated with a location that is known only imprecisely or within a general area rather than an exact position.
  • B. hasApproximateCoordinates
    Indicates that an entity is associated with location coordinates that are estimated or imprecise rather than exact.
  • C. hasApproximateNumberOfLocations
    Indicates that an entity is associated with an estimated or approximate count of locations, rather than an exact number.
  • D. exactLocationKnown
    Indicates that the precise geographic or spatial position of an entity is known and specified.
  • E. hasLocationComponent
    Indicates that something includes, is associated with, or is composed of a specific location-related part or element.
  • F. None of above.

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_69f349685f088190b8fda44083a018a9 completed April 30, 2026, 12:22 p.m.
NER Named-entity recognition batch_69fe744faca881908e11e90e0a35653f completed May 8, 2026, 11:39 p.m.
PD Predicate disambiguation batch_69fe734cbf7081909a552c5cf3b5ea59 completed May 8, 2026, 11:35 p.m.
Created at: May 1, 2026, 1:33 a.m.