Triple
T1687601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul Barras |
E36477
|
entity |
| Predicate | endOfPosition |
P20778
|
FINISHED |
| Object | resignation from the Directory in 1799 |
—
|
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: resignation from the Directory in 1799 | Statement: [Paul Barras, endOfPosition, resignation from the Directory in 1799]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endOfPosition Context triple: [Paul Barras, endOfPosition, resignation from the Directory in 1799]
-
A.
notablePositionEnd
chosen
Indicates the point in time or event at which an entity’s notable position, role, or office comes to an end.
-
B.
rangeEnd
Indicates the endpoint or upper boundary value of a specified range in a relationship or measurement.
-
C.
endEvent
Indicates that one event or process marks the termination or conclusion of another event or process.
-
D.
canonicalOrderEnd
Indicates the point or boundary at which a defined canonical or standard ordering of elements, events, or components concludes.
-
E.
hasEnding
Indicates that one entity concludes with, or terminates in, another entity (such as a specific substring, segment, or final component).
- 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_69a886151508819084fa7f1ce6e05577 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf3359ce48190803b322db8ad6027 |
completed | March 6, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69aa61b71cec8190b273588051058ebd |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:29 p.m.