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.