Triple
T23512632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Adamson v. California |
E572466
|
entity |
| Predicate | criminalChargeContext |
P77292
|
FINISHED |
| Object | murder conviction in California state court |
—
|
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: murder conviction in California state court | Statement: [Adamson v. California, criminalChargeContext, murder conviction in California state court]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: criminalChargeContext Context triple: [Adamson v. California, criminalChargeContext, murder conviction in California state court]
-
A.
crimeCharged
chosen
Indicates that legal authorities have formally accused an entity of committing a specific crime.
-
B.
crimeAccusation
Indicates that one entity formally accuses another entity of having committed a crime.
-
C.
arrestContext
Indicates that an arrest event occurs within a particular situational, legal, or environmental context that frames how and why the arrest takes place.
-
D.
criminalRecord
Indicates that an entity has a documented history of criminal offenses or convictions recorded by an authority.
-
E.
criminalType
Indicates the specific category or classification of crime associated with a criminal act or offender.
- 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_69e245b5e4208190bac8a6509867e394 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa7f583881909e78e8fe2e6e25fe |
completed | April 29, 2026, 6:51 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:07 p.m.