Triple
T6280908
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | kidnapping and assault case involving Stompie Seipei |
E140777
|
entity |
| Predicate | bodyDiscoveryLocation |
P47308
|
FINISHED |
| Object | near Soweto |
—
|
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: near Soweto | Statement: [kidnapping and assault case involving Stompie Seipei, bodyDiscoveryLocation, near Soweto]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: bodyDiscoveryLocation Context triple: [kidnapping and assault case involving Stompie Seipei, bodyDiscoveryLocation, near Soweto]
-
A.
locationInSystem
Indicates that one entity is situated within or belongs to the spatial or organizational bounds of a particular system.
-
B.
platformLocation
Indicates the spatial position or placement of a platform relative to a reference point or environment.
-
C.
portalLocation
Indicates that a portal is situated at or associated with a specific location.
-
D.
benchLocation
Indicates that a bench is located at or associated with a specific place or position.
-
E.
subjectLocation
chosen
Indicates that one entity is located at, in, or near the place or position specified by another 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_69c008cd17c8819082b82d3fbeb68047 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063ddb3a4819083455f6da854f8a9 |
completed | March 22, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69c05608a5608190b22a1fdc4060470d |
completed | March 22, 2026, 8:50 p.m. |
Created at: March 22, 2026, 4:26 p.m.