Triple
T19782936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Parks |
E475182
|
entity |
| Predicate | implementsActivity |
P26610
|
FINISHED |
| Object | anti-poaching operations |
—
|
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: anti-poaching operations | Statement: [African Parks, implementsActivity, anti-poaching operations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: implementsActivity Context triple: [African Parks, implementsActivity, anti-poaching operations]
-
A.
implementsAct
chosen
Indicates that one entity carries out, executes, or puts into effect a specified act, plan, or directive associated with another entity.
-
B.
exportActivity
Indicates an action where goods, services, or data are sent out from one entity or region to another for trade or distribution across borders.
-
C.
supportsActivity
Indicates that one entity provides the necessary conditions, resources, or environment for another entity’s activity to occur or be sustained.
-
D.
performActivities
Indicates that an entity carries out or engages in one or more specified activities or tasks.
-
E.
hasActivityIn
Indicates that an entity engages in or performs a particular activity within a specified context, location, or domain.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653852e848190b8971981a164e8f9 |
completed | April 20, 2026, 4:25 p.m. |
| PD | Predicate disambiguation | batch_69e53053ed2881908400becdfada7fd3 |
completed | April 19, 2026, 7:43 p.m. |
Created at: April 10, 2026, 1:49 p.m.