Triple
T16998365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Secretary General of the Union for the Mediterranean |
E412374
|
entity |
| Predicate | fourthHolderStartDate |
P89786
|
FINISHED |
| Object | 2018 |
—
|
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: 2018 | Statement: [Secretary General of the Union for the Mediterranean, fourthHolderStartDate, 2018]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fourthHolderStartDate Context triple: [Secretary General of the Union for the Mediterranean, fourthHolderStartDate, 2018]
-
A.
fourthOfficeHolderStartDate
chosen
Indicates the date on which the fourth person to hold a particular office or position began their term.
-
B.
thirdOfficeHolderStartDate
Indicates the date on which the third person to hold a particular office or position began their term.
-
C.
previousHolderStartDate
Indicates the date on which the immediately preceding holder of something (e.g., a position, title, or asset) began their tenure or ownership.
-
D.
firstHolderDate
Indicates the date on which an entity first became the holder or owner of another entity (e.g., an asset, title, or right).
-
E.
fourthPlanStartYear
Indicates the calendar year in which the entity’s fourth plan or planning period begins.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d37c16d081908ea5e25c992cb254 |
completed | April 18, 2026, 6:54 p.m. |
| PD | Predicate disambiguation | batch_69e35d552bc08190af17ef7659e094ef |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:32 a.m.