Triple
T23525836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pickens County Courthouse (Carrollton) |
E576429
|
entity |
| Predicate | hasWindowWithLegend |
P103592
|
FINISHED |
| Object | north-facing upstairs window |
—
|
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: north-facing upstairs window | Statement: [Pickens County Courthouse (Carrollton), hasWindowWithLegend, north-facing upstairs window]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasWindowWithLegend Context triple: [Pickens County Courthouse (Carrollton), hasWindowWithLegend, north-facing upstairs window]
-
A.
hasWindowDepicting
Indicates that one entity possesses a window on which the other entity is depicted or represented.
-
B.
hasLegendAssociatedWith
Indicates that something is connected to or accompanied by a traditional story, myth, or legend.
-
C.
hasSiblingInLegend
Indicates that one entity is described as the sibling of another entity within a mythological or legendary narrative.
-
D.
hasHistoricalLegend
Indicates that there exists a traditional story, myth, or legend associated with the subject, typically rooted in historical or cultural narratives.
-
E.
hasMediaLegend
chosen
Indicates that an entity is associated with a media-specific legend or caption that explains or describes that media.
- 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_69e245f5a8848190a2ba42e271c6c31f |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1ac73be64819083e4a1c2c09551fb |
completed | April 29, 2026, 7 a.m. |
| PD | Predicate disambiguation | batch_69f1189d75b48190a1c01928a993c9fb |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:09 p.m.