Triple
T3770597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | State Secretary |
E82786
|
entity |
| Predicate | termEndsWith |
P3587
|
FINISHED |
| Object | change of government in many systems |
—
|
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: change of government in many systems | Statement: [State Secretary, termEndsWith, change of government in many systems]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: termEndsWith Context triple: [State Secretary, termEndsWith, change of government in many systems]
-
A.
blendsWith
Indicates that one entity can be mixed or combined smoothly with another to form a uniform or harmonious result.
-
B.
endsWith
Indicates that one entity terminates with, or has as its final part, the sequence or element represented by the other entity.
-
C.
endedWith
chosen
Indicates that one event, process, or state concluded with or was finalized by another specified event, condition, or outcome.
-
D.
hasEnding
Indicates that one entity concludes with, or terminates in, another entity (such as a specific substring, segment, or final component).
-
E.
termEndOfLastHolder
Indicates that something marks the end point of the term or tenure of the most recent previous holder of a role, position, or asset.
- 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_69ad8b207b0081909d2b48843fbd8795 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adcc307cf8819090730b5e697bb197 |
completed | March 8, 2026, 7:21 p.m. |
| PD | Predicate disambiguation | batch_69adc04ec36c8190bd5b944d4f4d32aa |
completed | March 8, 2026, 6:30 p.m. |
Created at: March 8, 2026, 3:36 p.m.