Triple
T5255483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Joe Adonis |
E118685
|
entity |
| Predicate | criminalSphere |
P21640
|
FINISHED |
| Object | New York organized crime |
—
|
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: New York organized crime | Statement: [Joe Adonis, criminalSphere, New York organized crime]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: criminalSphere Context triple: [Joe Adonis, criminalSphere, New York organized crime]
-
A.
committedCrime
Indicates that an entity has carried out or been responsible for a criminal act or offense.
-
B.
crimeType
Indicates the specific category or nature of the crime associated with an event or entity.
-
C.
thirdMystery
Indicates a relationship where an entity is associated with the third mystery in a defined ordered set of mysteries (such as stages, secrets, or thematic elements).
-
D.
criminalOrganization
chosen
Indicates that the subject is an organized group engaged in ongoing illegal activities, often with structured hierarchy and coordination.
-
E.
featuresMurderInvestigation
Indicates that the subject involves or includes a murder investigation as a central element or storyline.
- 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_69bd446978108190bb5f9c5c23d93f88 |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd7ba2f5d08190850529659901ae0f |
completed | March 20, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69bd77c30bac8190a883ca45da35d667 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:50 p.m.