Triple

T35680270
Position Surface form Disambiguated ID Type / Status
Subject Belgian railway line 96 E1030985 entity
Predicate hasSectionParallelTo P201766 FINISHED
Object HSL 1 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: HSL 1 | Statement: [Belgian railway line 96, hasSectionParallelTo, HSL 1]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasSectionParallelTo
Context triple: [Belgian railway line 96, hasSectionParallelTo, HSL 1]
  • A. hasSectionAlong
    Indicates that one entity includes or runs along a specific segment or portion of another entity.
  • B. hasSectionIn
    Indicates that one entity contains or includes another entity as a section or subdivision within it.
  • C. isPartiallyParallelTo
    Indicates that two entities are aligned in roughly the same direction but not exactly parallel, sharing only a partial or approximate parallel relationship.
  • D. has2DSection
    Indicates that one entity represents a two-dimensional cross-sectional view or slice of another entity.
  • E. hasSectionOn
    Indicates that one entity (typically a document or resource) contains a dedicated section or part that specifically addresses or discusses another entity or topic.
  • F. None of above. chosen

Provenance (4 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_69f76e0bb6608190ad3a1880be54a17d completed May 3, 2026, 3:47 p.m.
NER Named-entity recognition batch_6a001cc0ff588190bb7c8a6fd427d02b completed May 10, 2026, 5:50 a.m.
PD Predicate disambiguation batch_6a001b3ea18c8190aeda7a32b2697490 completed May 10, 2026, 5:44 a.m.
PDg Predicate description generation batch_6a001cc053ac8190927768a4ecb023b9 completed May 10, 2026, 5:50 a.m.
Created at: May 3, 2026, 4:05 p.m.