Triple

T6624914
Position Surface form Disambiguated ID Type / Status
Subject Saint-Germain-de-Montgommery E149770 entity
Predicate hasGeographicalDirectionInFrance P46910 FINISHED
Object northwest 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: northwest | Statement: [Saint-Germain-de-Montgommery, hasGeographicalDirectionInFrance, northwest]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasGeographicalDirectionInFrance
Context triple: [Saint-Germain-de-Montgommery, hasGeographicalDirectionInFrance, northwest]
  • A. directionFromParis
    Indicates the cardinal or relative compass direction of an entity as measured from Paris toward that entity.
  • B. geographicDirectionWithinCountry chosen
    Indicates that one place lies in a specified cardinal or intercardinal direction relative to another place within the same country.
  • C. geographicDirectionImpliedByName
    Indicates that the name of a place or feature suggests a specific geographic direction (e.g., north, south, east, west) relative to some reference.
  • D. containsDirectionOf
    Indicates that one entity includes or encompasses the directional orientation or path associated with another entity.
  • E. hasFrenchSector
    Indicates that an entity includes, controls, or is associated with a sector or area designated as French.
  • 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_69c687ed8a9c81908bb671717cb192ef completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6bdb88cc881908f35648c15a7dc85 completed March 27, 2026, 5:26 p.m.
PD Predicate disambiguation batch_69c6ad007c1c8190af425f51011c7ad1 completed March 27, 2026, 4:14 p.m.
Created at: March 27, 2026, 1:58 p.m.