Triple
T11058865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UNITA |
E261451
|
entity |
| Predicate | notableLeaderDeath |
P62391
|
FINISHED |
| Object | Jonas Savimbi was killed in combat in 2002 |
—
|
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: Jonas Savimbi was killed in combat in 2002 | Statement: [UNITA, notableLeaderDeath, Jonas Savimbi was killed in combat in 2002]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableLeaderDeath Context triple: [UNITA, notableLeaderDeath, Jonas Savimbi was killed in combat in 2002]
-
A.
notableDeath
Indicates that an entity’s death is considered significant or noteworthy in some context.
-
B.
notableCommanderKilledInAction
chosen
Indicates that a notable military commander associated with an entity was killed in action.
-
C.
notableBearerDeathYear
Indicates the year in which a notable bearer of the referenced name, title, or role died.
-
D.
honorsPersonDiedIn
Indicates that something serves as a tribute or commemoration to the person who died in a particular event, place, or circumstance.
-
E.
notableFormerLeader
Indicates that the subject was once a leader of the object and is recognized as particularly significant or prominent in that former leadership role.
- 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_69d6aa98650481908609c7c56bfa7902 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d798a4f3f88190a29710f64cef9d25 |
completed | April 9, 2026, 12:16 p.m. |
| PD | Predicate disambiguation | batch_69d7440da46c8190a77380d5d747ac9c |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:26 p.m.