Triple

T38390924
Position Surface form Disambiguated ID Type / Status
Subject Count of Perche E899713 entity
Predicate regionHistoricallyBordered P47008 FINISHED
Object Normandy NE NERFINISHED

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: Normandy | Statement: [Count of Perche, regionHistoricallyBordered, Normandy]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: regionHistoricallyBordered
Context triple: [Count of Perche, regionHistoricallyBordered, Normandy]
  • A. historicBoundaryFor chosen
    Indicates that one entity serves as a historical boundary or border associated with another entity, typically reflecting past territorial or administrative limits.
  • B. borderRegion
    Indicates a region that lies along or near the boundary separating two distinct geographic or political areas.
  • C. borderedBy
    Indicates that one entity shares a common boundary or edge with another entity.
  • D. borderHistory
    Indicates the historical changes, events, or status of borders between entities over time.
  • E. historicalRegionNowDividedBetween
    Indicates that a historical region has been partitioned and its territory is now split between two or more present-day political or administrative entities.
  • 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_69f76e5c9b808190b486523f5c2f817d completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_6a008e29f76881908e656dbbd7fceea3 completed May 10, 2026, 1:54 p.m.
PD Predicate disambiguation batch_6a008dc01b308190bc26e69814692f82 completed May 10, 2026, 1:53 p.m.
Created at: May 3, 2026, 4:31 p.m.