Triple
T23633290
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Julius Maada Bio |
E583673
|
entity |
| Predicate | leftOfficeAsHeadOfState |
P153345
|
FINISHED |
| Object | 1996-03 |
—
|
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: 1996-03 | Statement: [Julius Maada Bio, leftOfficeAsHeadOfState, 1996-03]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leftOfficeAsHeadOfState Context triple: [Julius Maada Bio, leftOfficeAsHeadOfState, 1996-03]
-
A.
headOfOffice
Indicates that one entity serves as the chief or leading authority in charge of a particular office or organizational unit.
-
B.
underHeadOfState
Indicates that one entity operates within the authority, jurisdiction, or leadership of a specified head of state.
-
C.
sharesHeadOfState
Indicates that two political entities have the same individual serving as their head of state.
-
D.
upperHeadOfState
Indicates that one entity serves as the highest-ranking head of state in relation to another entity (such as a country or political body).
-
E.
headOfGovernment
Indicates that one entity serves as the chief executive authority or leader of the government of another entity.
- F. None of above. chosen
Provenance (4 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_69e248fe1c2c8190ac914d2442ff3d26 |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b1ea269c8190a677e812d7471a98 |
completed | April 29, 2026, 7:23 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
| PDg | Predicate description generation | batch_69f138b8c9248190b059bc38a9a50958 |
completed | April 28, 2026, 10:46 p.m. |
Created at: April 17, 2026, 6:47 p.m.