Triple
T24370731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rhodesian Security Forces |
E614323
|
entity |
| Predicate | secondaryTheatre |
P48888
|
FINISHED |
| Object | Mozambique |
—
|
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: Mozambique | Statement: [Rhodesian Security Forces, secondaryTheatre, Mozambique]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secondaryTheatre Context triple: [Rhodesian Security Forces, secondaryTheatre, Mozambique]
-
A.
secondaryTheater
chosen
Indicates that an entity serves as a secondary or supporting theater or venue in relation to a primary one.
-
B.
primaryTheater
Indicates that a particular location or region is the main setting or principal area where an event, activity, or operation takes place.
-
C.
secondarySee
Indicates that one entity is referenced as an additional or alternative point of consultation or viewing in relation to another entity.
-
D.
secondaryStages
Indicates that one or more stages occur as subsequent or follow-up phases relative to an initial or primary stage in a process or sequence.
-
E.
secondAct
Indicates that an entity performs, participates in, or is associated with the second act or phase within a larger, ordered sequence of actions or events.
- 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_69e2d7e1e010819098b95eb3f905943d |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2938b95188190b8f7ee1098c6088a |
completed | April 29, 2026, 11:26 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2:01 a.m.