Triple
T28405219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arms of the Second French Empire |
E719507
|
entity |
| Predicate | endEventContext |
P44016
|
FINISHED |
| Object | Franco-Prussian War |
—
|
NE NERFINISHED |
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: Franco-Prussian War | Statement: [Arms of the Second French Empire, endEventContext, Franco-Prussian War]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endEventContext Context triple: [Arms of the Second French Empire, endEventContext, Franco-Prussian War]
-
A.
endEvent
Indicates that one event or process marks the termination or conclusion of another event or process.
-
B.
eventContext
chosen
Indicates the situational or background circumstances (such as time, place, conditions, or surrounding events) within which a particular event occurs or is interpreted.
-
C.
endUseEvent
Indicates an event marking the final or terminating use of something by an entity.
-
D.
endOfTermContext
Indicates the situational or temporal context associated with the conclusion of a defined term, period, or contractual duration.
-
E.
endOfRuleContext
Indicates that a particular parsing or evaluation rule has reached its terminating boundary within the current context.
- 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_69eff6efd1b08190ae3cefd4f11388a2 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64d6ef83881909b6015503c9e6470 |
completed | May 2, 2026, 7:15 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 1:23 a.m.