Triple
T23525837
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pickens County Courthouse (Carrollton) |
E576429
|
entity |
| Predicate | imageInWindowSaidToBe |
P37258
|
FINISHED |
| Object | face of a lynched man accused of arson |
—
|
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: face of a lynched man accused of arson | Statement: [Pickens County Courthouse (Carrollton), imageInWindowSaidToBe, face of a lynched man accused of arson]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: imageInWindowSaidToBe Context triple: [Pickens County Courthouse (Carrollton), imageInWindowSaidToBe, face of a lynched man accused of arson]
-
A.
hasWindowDepicting
Indicates that one entity possesses a window on which the other entity is depicted or represented.
-
B.
visualDepictionOnScreen
Indicates that one entity is visually shown or rendered on a screen as a depiction of another entity.
-
C.
imagedIn
chosen
Indicates that one entity appears within or is depicted in an image associated with another entity.
-
D.
visibilityInImages
Indicates how clearly or prominently an entity can be seen or detected within one or more images.
-
E.
imageOf
Indicates that one entity is a visual representation or depiction of 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_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.