Triple
T27629501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Speaker of the National Assembly of Pakistan |
E696298
|
entity |
| Predicate | holdsOfficeUntil |
P90799
|
FINISHED |
| Object | successor is elected |
—
|
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: successor is elected | Statement: [Speaker of the National Assembly of Pakistan, holdsOfficeUntil, successor is elected]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: holdsOfficeUntil Context triple: [Speaker of the National Assembly of Pakistan, holdsOfficeUntil, successor is elected]
-
A.
officeholderEndTime
Indicates the time or date at which a person’s term in a particular office or position comes to an end.
-
B.
candidacyEndDate
Indicates the date on which an entity’s period of candidacy or eligibility for a position, role, or status comes to an end.
-
C.
lastOfficeholderEndDate
chosen
Indicates the date on which the most recent officeholder’s term in a given position or office ended.
-
D.
remainedInForceUntil
Indicates that a rule, condition, or state continued to be valid or effective up to a specified point in time.
-
E.
candidacyEnd
Indicates the point in time or event at which an entity’s candidacy for a position, role, or office comes to an end.
- 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_69ef59092c8881908114ad184248cc46 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f63122c45c8190a6692f11dcf0e62f |
completed | May 2, 2026, 5:15 p.m. |
| PD | Predicate disambiguation | batch_69f62c1921008190a62675a31f66a875 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 2:20 p.m.