Triple
T37497532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prosecutor v. Germain Katanga |
E931868
|
entity |
| Predicate | crimeLocationCountry |
P61066
|
FINISHED |
| Object | Democratic Republic of the Congo |
—
|
NE NERFINISHED |
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: Democratic Republic of the Congo | Statement: [Prosecutor v. Germain Katanga, crimeLocationCountry, Democratic Republic of the Congo]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: crimeLocationCountry Context triple: [Prosecutor v. Germain Katanga, crimeLocationCountry, Democratic Republic of the Congo]
-
A.
crimeLocation
Indicates that a crime occurred at, or is associated with, a particular location.
-
B.
regionOfCrimes
Indicates the geographic area or jurisdiction in which the crimes occurred or are attributed to an entity.
-
C.
country of criminal activity
chosen
Indicates the country in which the criminal activity took place or was primarily carried out.
-
D.
crimeRate
Indicates the frequency or level of criminal activity occurring within a given area or population.
-
E.
countryWhereOccurred
Indicates the country in which a particular event, action, or occurrence took place.
- 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_69f76ec457a4819094eeb3aed9baac11 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fbacaf54648190811ea33b34907e8e |
completed | May 6, 2026, 9:03 p.m. |
| PD | Predicate disambiguation | batch_69fba883f770819091059c6f6c6af9f7 |
completed | May 6, 2026, 8:45 p.m. |
Created at: May 3, 2026, 4:17 p.m.