Triple
T16142557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | assassination of James A. Garfield |
E391696
|
entity |
| Predicate | targetOffice |
P23717
|
FINISHED |
| Object | 20th president of the United States |
—
|
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: 20th president of the United States | Statement: [assassination of James A. Garfield, targetOffice, 20th president of the United States]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: targetOffice Context triple: [assassination of James A. Garfield, targetOffice, 20th president of the United States]
-
A.
targetOfficeSought
Indicates the specific public or organizational office or position that an individual is seeking or running for.
-
B.
targetedOffice
chosen
Indicates that an action, event, or campaign was specifically directed at or focused on a particular office or organizational unit.
-
C.
targetWork
Indicates that one entity is the specific work (e.g., document, artwork, or project) that another entity is directed at, refers to, or is primarily concerned with.
-
D.
specifiesOffice
Indicates that an entity is assigned to or associated with a particular office or official position.
-
E.
mainOffice
Indicates that one location or office serves as the primary or central office for an organization or entity.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21d9082588190bc7e6ff491f0d94e |
completed | April 17, 2026, 11:46 a.m. |
| PD | Predicate disambiguation | batch_69e182885bc08190822ae7e8a4b8ac1f |
completed | April 17, 2026, 12:44 a.m. |
Created at: April 10, 2026, 5:01 a.m.