Triple
T8004689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South African general election, 1987 |
E186334
|
entity |
| Predicate | tookPlaceAmid |
P3824
|
FINISHED |
| Object | growing calls for negotiations with the African National Congress |
—
|
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: growing calls for negotiations with the African National Congress | Statement: [South African general election, 1987, tookPlaceAmid, growing calls for negotiations with the African National Congress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tookPlaceAmid Context triple: [South African general election, 1987, tookPlaceAmid, growing calls for negotiations with the African National Congress]
-
A.
tookPlaceFrom
Indicates that an event or occurrence started or was ongoing beginning at a specified time or location.
-
B.
tookPlaceInAdministrativeEntity
Indicates that an event or occurrence happened within the jurisdiction or boundaries of a specific administrative entity.
-
C.
tookPlaceInYear
Indicates that an event or occurrence happened during a specific calendar year.
-
D.
occurredDuring
chosen
Indicates that one event or action took place within the temporal span of another event or time period.
-
E.
tookPlaceAfter
Indicates that one event or occurrence happened later in time than another event or occurrence.
- 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_69ca82aaaf24819084b94d18f699ba53 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3cf5fb588190ada4ec7d8087619c |
completed | March 31, 2026, 3:18 a.m. |
| PD | Predicate disambiguation | batch_69cb0483d3b48190b250c7603d747bca |
completed | March 30, 2026, 11:17 p.m. |
Created at: March 30, 2026, 5:18 p.m.