Triple
T2235529
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lucy Flucker Knox |
E49270
|
entity |
| Predicate | marriedToRank |
P37264
|
FINISHED |
| Object | American Revolutionary War general |
—
|
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 Revolutionary War general | Statement: [Lucy Flucker Knox, marriedToRank, American Revolutionary War general]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marriedToRank Context triple: [Lucy Flucker Knox, marriedToRank, American Revolutionary War general]
-
A.
marriedIn
Indicates that two entities entered into a marital relationship at a specific place or within a particular jurisdiction.
-
B.
marriedInto
Indicates that one entity became connected to another’s family or group through marriage, rather than by birth or prior membership.
-
C.
metSpouseAt
Indicates that one person first encountered or became acquainted with their spouse at a particular place, event, or time.
-
D.
numberOfMarriagesOfSpouse
Indicates the total count of times the referenced spouse has been married.
-
E.
marriedAfter
Indicates that one marriage occurred later in time than another specified marriage.
- F. None of above. chosen
Provenance (4 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_69a88aa84bdc819086df50e9c20b301e |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc093ba0c819091df09a0e018fce1 |
completed | March 7, 2026, 6:07 a.m. |
| PD | Predicate disambiguation | batch_69abbdafc07881909101266a33ae7031 |
completed | March 7, 2026, 5:54 a.m. |
| PDg | Predicate description generation | batch_69abbf9c77fc8190a323bcaf644fb2c5 |
completed | March 7, 2026, 6:03 a.m. |
Created at: March 4, 2026, 7:47 p.m.