Triple
T11779058
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hubbardton engagement |
E280092
|
entity |
| Predicate | involvedRetreatOf |
P83766
|
FINISHED |
| Object | American forces from Fort Ticonderoga |
—
|
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: American forces from Fort Ticonderoga | Statement: [Hubbardton engagement, involvedRetreatOf, American forces from Fort Ticonderoga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedRetreatOf Context triple: [Hubbardton engagement, involvedRetreatOf, American forces from Fort Ticonderoga]
-
A.
partOfRetreatOf
chosen
Indicates that one entity participates as a component or segment within the broader retreat or withdrawal of another entity.
-
B.
retreatedDuring
Indicates that an entity withdrew or pulled back during the time span or event specified by another entity.
-
C.
wasPoliticalRetreatOf
Indicates that one entity served as a political retreat or refuge location for another entity.
-
D.
eraOfMajorRetreat
Indicates a time period during which a significant withdrawal, decline, or pullback of something (such as forces, influence, or presence) occurred.
-
E.
operatesRetreats
Indicates that an entity manages and runs one or more retreat programs or retreat locations.
- 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a8c2e8b08190a31b1e284fca2aee |
completed | April 10, 2026, 7:37 a.m. |
| PD | Predicate disambiguation | batch_69d8a242cd8c819086ed6c5f292dc8cb |
completed | April 10, 2026, 7:09 a.m. |
Created at: April 8, 2026, 9:42 p.m.