Triple
T37144974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Martyrs of the country under the Mobutu regime |
E920218
|
entity |
| Predicate | opposedRegimeOf |
P115953
|
FINISHED |
| Object | Mobutu Sese Seko |
—
|
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: Mobutu Sese Seko | Statement: [Martyrs of the country under the Mobutu regime, opposedRegimeOf, Mobutu Sese Seko]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opposedRegimeOf Context triple: [Martyrs of the country under the Mobutu regime, opposedRegimeOf, Mobutu Sese Seko]
-
A.
countryOfOpposition
Indicates the country in which an entity faces opposition, resistance, or adversarial activity.
-
B.
opposedPoliticalEntity
Indicates that one political entity is in opposition or conflict with another in terms of policies, ideology, or power.
-
C.
opposedRegent
Indicates that one party actively resisted, challenged, or worked against the authority or actions of a regent.
-
D.
opposedAdministration
chosen
Indicates that one entity actively resisted, challenged, or worked against the governance, policies, or authority exercised by another entity or administration.
-
E.
opponentGovernmentType
Indicates the form or system of government of an opposing or rival entity in a given context.
- 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fd7b0503a08190ba07338365b6fcc9 |
completed | May 8, 2026, 5:56 a.m. |
| PD | Predicate disambiguation | batch_69fd7a9733dc81909199f453c0cc2bc1 |
completed | May 8, 2026, 5:54 a.m. |
Created at: May 3, 2026, 4:15 p.m.