Triple
T3558998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queen's Rangers |
E75287
|
entity |
| Predicate | serviceEndReason |
P11350
|
FINISHED |
| Object | end of the American Revolutionary War |
—
|
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: end of the American Revolutionary War | Statement: [Queen's Rangers, serviceEndReason, end of the American Revolutionary War]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceEndReason Context triple: [Queen's Rangers, serviceEndReason, end of the American Revolutionary War]
-
A.
originalServiceEnded
Indicates that a previously existing or initial service has come to an end or has been terminated.
-
B.
supportEndedIn
Indicates that a previously existing support relationship between entities has come to an end at a specific point in time.
-
C.
reasonForDiscontinuation
chosen
Indicates that one entity specifies the cause or justification for stopping, ending, or withdrawing another entity, process, or activity.
-
D.
serviceEndEEOC
Indicates the point in time when an employee’s service or employment ends for purposes related to EEOC reporting or compliance.
-
E.
officeEnded
Indicates that a person’s term in an office or position has concluded at a specified time or under certain conditions.
- 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_69ad85d45090819086f34fb85d850a1e |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc0881d50819092332491b9527c9d |
completed | March 8, 2026, 6:31 p.m. |
| PD | Predicate disambiguation | batch_69adb834779081908468e182d5f6cf02 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:20 p.m.