Triple
T28942501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Crime in America |
E730488
|
entity |
| Predicate | authorPreviouslyHeldOffice |
P112779
|
FINISHED |
| Object | United States Attorney General |
—
|
NE NERFINISHED |
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: United States Attorney General | Statement: [Crime in America, authorPreviouslyHeldOffice, United States Attorney General]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorPreviouslyHeldOffice Context triple: [Crime in America, authorPreviouslyHeldOffice, United States Attorney General]
-
A.
officePreviouslyHeldBy
Indicates that a particular office or position was formerly occupied by a specified person or entity.
-
B.
heldPoliticalOfficeIn
Indicates that an entity served in a political office or position within a specified governmental body or jurisdiction.
-
C.
builtUnderPoliticalOffice
Indicates that the construction or creation of something occurred during the tenure of a particular political office or officeholder.
-
D.
hasHistoricalOfficeHolder
Indicates that an office, position, or role has been held by a specific person at some point in the past.
-
E.
hasMemberWhoHeldOffice
chosen
Indicates that a group or organization includes at least one member who has held a specified office or position.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: April 28, 2026, 8:37 a.m.