Triple
T24204512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Casey Welson |
E600069
|
entity |
| Predicate | modeOfAbduction |
P23389
|
FINISHED |
| Object | car trunk confinement |
—
|
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: car trunk confinement | Statement: [Casey Welson, modeOfAbduction, car trunk confinement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: modeOfAbduction Context triple: [Casey Welson, modeOfAbduction, car trunk confinement]
-
A.
abductionMotif
chosen
Indicates a relationship where an event, narrative, or depiction involves the motif of one entity abducting or forcibly carrying off another.
-
B.
possibleJudgment
Indicates a potential or anticipated judgment, decision, or evaluative outcome that could be made about an entity or situation.
-
C.
reasoningType
Indicates the specific kind or mode of reasoning applied in deriving a conclusion or making an inference between entities.
-
D.
presumption
Indicates that one party assumes or takes for granted a particular fact, condition, or state about another, often without definitive proof.
-
E.
canReasonAbout
Indicates that one entity has the capability to understand, analyze, or draw inferences about another entity or subject.
- 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_69e288ceaab88190899d0acb5931591d |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f27ca52cb881908c99913ea93bc88e |
completed | April 29, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69f1c43e55688190b55fc20274ed471c |
completed | April 29, 2026, 8:41 a.m. |
Created at: April 17, 2026, 11:37 p.m.