Triple
T5575535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rose McConnell Long |
E146308
|
entity |
| Predicate | officeAssumedAsResultOf |
P54607
|
FINISHED |
| Object | assassination of Huey P. Long |
—
|
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: assassination of Huey P. Long | Statement: [Rose McConnell Long, officeAssumedAsResultOf, assassination of Huey P. Long]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeAssumedAsResultOf Context triple: [Rose McConnell Long, officeAssumedAsResultOf, assassination of Huey P. Long]
-
A.
officeAssumedFrom
chosen
Indicates that one party has taken over or begun holding an office or position previously held by another party.
-
B.
officeAssumedByWinner
Indicates that a particular office or position is taken up or assumed by the winner of an election or contest.
-
C.
officeSucceededBy
Indicates that one office or position is followed or replaced by another office or position in a succession sequence.
-
D.
officeInvolved
Indicates that a particular office or organizational unit is involved or participates in a specified event, action, or relationship.
-
E.
layOffice
Indicates that one entity holds or occupies a particular office, position, or role in relation to another 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_69c008ffed108190a084602227af6157 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c02067e8d8819090a006cb266da5fe |
completed | March 22, 2026, 5:01 p.m. |
| PD | Predicate disambiguation | batch_69c01b147cc081909237f3f2967d4cb8 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:37 p.m.