Triple
T20084763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Buffalo crime family |
E500095
|
entity |
| Predicate | criminalEconomySector |
P16022
|
FINISHED |
| Object | construction industry racketeering |
—
|
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: construction industry racketeering | Statement: [Buffalo crime family, criminalEconomySector, construction industry racketeering]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: criminalEconomySector Context triple: [Buffalo crime family, criminalEconomySector, construction industry racketeering]
-
A.
criminalOrganization
Indicates that the subject is an organized group engaged in ongoing illegal activities, often with structured hierarchy and coordination.
-
B.
criminalType
Indicates the specific category or classification of crime associated with a criminal act or offender.
-
C.
criminalSpecialization
Indicates that an individual focuses their criminal activity on a particular type of offense or crime category.
-
D.
economicSectorSourceOfWealth
chosen
Indicates that a particular economic sector is the primary source from which an entity derives its wealth or income.
-
E.
crimeType
Indicates the specific category or nature of the crime associated with an event or 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_69da627770948190997f486f9a2e370f |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655a2d2c81908a6b8fd2f209a825 |
completed | April 20, 2026, 5:41 p.m. |
| PD | Predicate disambiguation | batch_69e54cf369b88190931532420517dac7 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:41 p.m.