Triple
T18353923
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Trial of Tom Dula in 1868 |
E439740
|
entity |
| Predicate | originalCrimeLocation |
P59762
|
FINISHED |
| Object | Wilkes County, North Carolina |
—
|
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: Wilkes County, North Carolina | Statement: [Trial of Tom Dula in 1868, originalCrimeLocation, Wilkes County, North Carolina]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalCrimeLocation Context triple: [Trial of Tom Dula in 1868, originalCrimeLocation, Wilkes County, North Carolina]
-
A.
crimeLocation
chosen
Indicates that a crime occurred at, or is associated with, a particular location.
-
B.
positionOnCrime
Indicates a stance, opinion, or policy position that an entity holds regarding crime or crime-related issues.
-
C.
regionOfCrimes
Indicates the geographic area or jurisdiction in which the crimes occurred or are attributed to an entity.
-
D.
targetOfCrime
Indicates that the subject is the person, organization, or entity against whom the referenced crime is committed.
-
E.
committedCrime
Indicates that an entity has carried out or been responsible for a criminal act or offense.
- 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_69d8b918221c8190a9f7b563d64ac677 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e516d37bc08190abc9b4e8c937c914 |
completed | April 19, 2026, 5:54 p.m. |
| PD | Predicate disambiguation | batch_69e44fe91bc08190906518e1b120fcf0 |
completed | April 19, 2026, 3:45 a.m. |
Created at: April 10, 2026, 10:37 a.m.