Triple
T35713871
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Central Anti-Corruption Bureau |
E1031942
|
entity |
| Predicate | hasInvestigativePowers |
P192092
|
FINISHED |
| Object | yes |
—
|
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: yes | Statement: [Central Anti-Corruption Bureau, hasInvestigativePowers, yes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasInvestigativePowers Context triple: [Central Anti-Corruption Bureau, hasInvestigativePowers, yes]
-
A.
hasPolicePowersIn
Indicates that an entity possesses official police authority or jurisdiction within a specified area or region.
-
B.
hasOperationalPowers
chosen
Indicates that an entity possesses the authority or capability to perform specific operational actions or functions.
-
C.
hasRegulatoryPower
Indicates that one entity possesses formal authority to create, enforce, or oversee rules and regulations governing another entity or activity.
-
D.
lawEnforcementPowers
Indicates that an entity possesses official authority and legal powers to enforce laws, maintain public order, and carry out related policing actions.
-
E.
hasPublicAuthority
Indicates that an entity possesses official power or legal authority to act on behalf of the public or a governing body.
- 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_69f76e0df1d08190965b1c6dff94c391 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a007aa8d3a481908543f9b5d562a90c |
completed | May 10, 2026, 12:31 p.m. |
| PD | Predicate disambiguation | batch_6a007a44996481908688ccfdbc56511d |
completed | May 10, 2026, 12:29 p.m. |
Created at: May 3, 2026, 4:05 p.m.