Triple
T28942500
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crime in America |
E730488
|
entity |
| Predicate | authorPositionAtTime |
P184597
|
FINISHED |
| Object | former United States Attorney 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: former United States Attorney General | Statement: [Crime in America, authorPositionAtTime, former United States Attorney General]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorPositionAtTime Context triple: [Crime in America, authorPositionAtTime, former United States Attorney General]
-
A.
positionOfAuthor
Indicates the spatial or organizational location associated with an author in relation to some reference context.
-
B.
positionAt
Indicates that one entity is located at, or occupies, a specific spatial position relative to another entity or reference frame.
-
C.
endTimePosition
Indicates the temporal position or point in time at which an event, state, or interval comes to an end.
-
D.
positionOfAnnouncer
Indicates the spatial location or placement of the announcer relative to other relevant entities or context.
-
E.
positionOnRecord
Indicates the specific place or rank an item occupies within an ordered record or listing.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f7b365288c8190bcb11fcfba028737 |
completed | May 3, 2026, 8:43 p.m. |
| PD | Predicate disambiguation | batch_69f7b1b8a9fc8190a1279e67a2d12707 |
completed | May 3, 2026, 8:36 p.m. |
| PDg | Predicate description generation | batch_69f7b2f2b9ac8190aa05b8a1aa18ec2d |
completed | May 3, 2026, 8:41 p.m. |
Created at: April 28, 2026, 8:37 a.m.