Triple

T4558842
Position Surface form Disambiguated ID Type / Status
Subject Roman lictor E120544 entity
Predicate clearedWayFor P29688 FINISHED
Object magistrate 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: magistrate | Statement: [Roman lictor, clearedWayFor, magistrate]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: clearedWayFor
Context triple: [Roman lictor, clearedWayFor, magistrate]
  • A. hasNavigationClearance
    Indicates that an entity has been granted authorization to navigate through a specified area or along a particular route.
  • B. navigationClearanceType
    Indicates the specific type or category of clearance granted for a navigation-related operation or movement.
  • C. hasRightOfWay chosen
    Indicates that one entity is entitled to proceed or act before another in a shared space or interaction, without having to yield.
  • D. firstEntranceClearedBy
    Indicates that the subject’s first entrance or initial access point was cleared, authorized, or made passable by the specified agent or process.
  • E. clearanceBelow
    Indicates that one entity is positioned at a lower vertical clearance level than another, typically with less space between it and an underlying reference surface.
  • 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_69bd4636f1648190a701445c2fcd9c17 completed March 20, 2026, 1:05 p.m.
NER Named-entity recognition batch_69bd5829cc34819086ad2ae58446502e completed March 20, 2026, 2:22 p.m.
PD Predicate disambiguation batch_69bd52254c648190a5144cfe8fa7e409 completed March 20, 2026, 1:56 p.m.
Created at: March 20, 2026, 1:09 p.m.