Triple

T36628029
Position Surface form Disambiguated ID Type / Status
Subject OSS E904228 entity
Predicate hasLineColorAssociation P183414 FINISHED
Object green (Line 2 Bloor–Danforth color) 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: green (Line 2 Bloor–Danforth color) | Statement: [OSS, hasLineColorAssociation, green (Line 2 Bloor–Danforth color)]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasLineColorAssociation
Context triple: [OSS, hasLineColorAssociation, green (Line 2 Bloor–Danforth color)]
  • A. isColorCodedLine
    Indicates that a line is represented or distinguished using specific colors according to a coding scheme.
  • B. hasFacadeColorAssociation
    Indicates an association between a building’s facade and a specific color or set of colors used on it.
  • C. usesLineColour chosen
    Indicates that one entity employs or is associated with the line color defined or provided by another entity.
  • D. hasColorReference
    Indicates that one entity serves as a reference or source for determining or specifying the color associated with another entity.
  • E. hasLineStyle
    Indicates that one entity is associated with or uses a particular style or pattern of line representation in relation to another entity.
  • 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_69f76e6ae750819096911e6e2d4d12c5 completed May 3, 2026, 3:48 p.m.
NER Named-entity recognition batch_69fef112398081909237c3872345968b completed May 9, 2026, 8:32 a.m.
PD Predicate disambiguation batch_69feefb14ec08190ab401987d8c84a23 completed May 9, 2026, 8:26 a.m.
Created at: May 3, 2026, 4:11 p.m.